Daily Papers

Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the complexity of learning steps has limited its applications to many 3D real-world. To address this limitation, we propose Point Straight Flow (PSF), a model that exhibits impressive performance using one step. Our idea is based on the reformulation of the standard diffusion model, which optimizes the curvy learning trajectory into a straight path. Further, we develop a distillation strategy to shorten the straight path into one step without a performance loss, enabling applications to 3D real-world with latency constraints. We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods. On real-world applications such as point cloud completion and training-free text-guided generation in a low-latency setup, PSF performs favorably.

This paper presents a streaming extension for the Sortformer speaker diarization framework, whose key property is the arrival-time ordering of output speakers. The proposed approach employs an Arrival-Order Speaker Cache (AOSC) to store frame-level acoustic embeddings of previously observed speakers. Unlike conventional speaker-tracing buffers, AOSC orders embeddings by speaker index corresponding to their arrival time order, and is dynamically updated by selecting frames with the highest scores based on the model's past predictions. Notably, the number of stored embeddings per speaker is determined dynamically by the update mechanism, ensuring efficient cache utilization and precise speaker tracking. Experiments on benchmark datasets confirm the effectiveness and flexibility of our approach, even in low-latency setups. These results establish Streaming Sortformer as a robust solution for real-time multi-speaker tracking and a foundation for streaming multi-talker speech processing.

Agricultural UAV research requires simulators that integrate realistic 3D scenes, high-fidelity vehicle dynamics, and robotics middleware, while remaining practical to deploy across heterogeneous development machines. We present Droneulator, a portable UAV simulator architecture that combines RotorPy for multirotor dynamics with Godot 4 for rendering and sensor generation. Droneulator exposes both PX4-based control and a lightweight WebSocket command path, and publishes synchronised visual and state streams through a Zenoh-based ROS~2-compatible pipeline. This integration enables a single stack to support inspection-oriented data capture, ROS~2/PX4 local planning, and reinforcement learning experiments without modifying the simulator infrastructure. We present quantified validation of the current system across three agricultural UAV workflows: tree-scale image collection for 3D reconstruction with COLMAP, local planning around canopy obstacles using EGO-Planner, and closed-loop reinforcement learning through a custom Gymnasium environment. In the reported setup, the results show that the simulator can sustain low-latency sensing, support reconstruction-oriented data collection under varying capture density, execute collision-free local planning around canopy obstacles, and support stable depth-sensing-based policy training for obstacle-aware navigation. Together, these results show the potential of Droneulator for agricultural UAV inspection, planning, and learning within one deployable stack.

Driven by the progress in efficient embedded processing, there is an accelerating trend toward running machine learning models directly on wearable Brain-Machine Interfaces (BMIs) to improve portability and privacy and maximize battery life. However, achieving low latency and high classification performance remains challenging due to the inherent variability of electroencephalographic (EEG) signals across sessions and the limited onboard resources. This work proposes a comprehensive BMI workflow based on a CNN-based Continual Learning (CL) framework, allowing the system to adapt to inter-session changes. The workflow is deployed on a wearable, parallel ultra-low power BMI platform (BioGAP). Our results based on two in-house datasets, Dataset A and Dataset B, show that the CL workflow improves average accuracy by up to 30.36% and 10.17%, respectively. Furthermore, when implementing the continual learning on a Parallel Ultra-Low Power (PULP) microcontroller (GAP9), it achieves an energy consumption as low as 0.45mJ per inference and an adaptation time of only 21.5ms, yielding around 25h of battery life with a small 100mAh, 3.7V battery on BioGAP. Our setup, coupled with the compact CNN model and on-device CL capabilities, meets users' needs for improved privacy, reduced latency, and enhanced inter-session performance, offering good promise for smart embedded real-world BMIs.

Large Language Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving instances can improve resource utilization, but directly applying this approach to Prefill/Decode (P/D) disaggregated systems introduces severe load imbalance, as fluctuating request mixes alter the intrinsic P/D ratio. Existing dynamic adjustment techniques cannot keep up with the bursty traffic patterns of online services. We propose a latency-constraint disaggregated architecture, which separates cluster resources into latency-strict and latency-relaxed pools based on task latency requirements. This design enables flexible placement of offline decode tasks, mitigating P/D imbalance while preserving online performance. To fully exploit this flexibility, we propose (1) a bottleneck-based scheduler guided by a Roofline-based performance model for performance bottleneck based scheduling, and (2) a fast preemption mechanism that strictly enforces Service Level Objectives (SLOs) for online requests. Experiments on real-world traces show that compared to existing offline system approaches, our method improves offline throughput by up to 3x, while maintaining online request SLOs.

Large language models can generate code and call tools with remarkable fluency, yet deploying them as practical software engineering assistants still expose stubborn gaps: finite context windows, single mistakes that derail entire sessions, agents that get stuck in dead ends, AI slop, and generated changes that are difficult to review or revert. We present KISS Sorcar, a general-purpose assistant and integrated development environment (IDE) built on top of the KISS Agent Framework, a stupidly-simple AI agent framework of roughly 1,850 lines of code. The framework addresses these gaps using a robust system prompt and through a five-layer agent hierarchy in which each layer adds exactly one concern: budget-tracked ReAct execution, automatic continuation across sub-sessions via summarization, coding, and browser tools with parallel sub-agents, persistent multi-turn chat with history recall, and git worktree isolation so every task runs on its own branch. To assess the power of the KISS agent framework, we implemented KISS Sorcar as a free, open-source Visual Studio Code extension that runs locally and effectively for long-horizon tasks, and supports browser automation, multimodal input, and Docker containers. In this research, we deliberately prioritize output quality over latency: giving a frontier model adequate time to validate its own output -- running linters, type checkers, and tests -- dramatically reduces the low-quality code that plagues faster but less thorough agents. The entire system was built using itself in 4.5 months, providing a continuous stress test in which any agent-introduced bug immediately impairs its own ability to work. On Terminal Bench 2.0, KISS Sorcar achieves a 62.2% overall pass rate with Claude Opus 4.6, comparing favorably to Claude Code (58%) and Cursor Composer 2 (61.7).

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across all users and requests. We find that this strategy not only leads to strong prefill-decoding interferences but also couples the resource allocation and parallelism plans for both phases. LLM applications often emphasize individual latency for each phase: time to first token (TTFT) for the prefill phase and time per output token (TPOT) of each request for the decoding phase. In the presence of stringent latency requirements, existing systems have to prioritize one latency over the other, or over-provision compute resources to meet both. DistServe assigns prefill and decoding computation to different GPUs, hence eliminating prefill-decoding interferences. Given the application's TTFT and TPOT requirements, DistServe co-optimizes the resource allocation and parallelism strategy tailored for each phase. DistServe also places the two phases according to the serving cluster's bandwidth to minimize the communication caused by disaggregation. As a result, DistServe significantly improves LLM serving performance in terms of the maximum rate that can be served within both TTFT and TPOT constraints on each GPU. Our evaluations show that on various popular LLMs, applications, and latency requirements, DistServe can serve 4.48x more requests or 10.2x tighter SLO, compared to state-of-the-art systems, while staying within latency constraints for > 90% of requests.

Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In latency-sensitive applications, rather than waiting for the full utterance, translations should be spoken as soon as the information in the input is present. In this work, we introduce a system for simultaneous S2ST targeting real-world use cases. Our system supports translation from 57 languages to English with tunable parameters for dynamically adjusting the latency of the output -- including four policies for determining when to speak an output sequence. We show that these policies achieve offline-level accuracy with minimal increases in latency over a Greedy (wait-k) baseline. We open-source our evaluation code and interactive test script to aid future SimulS2ST research and application development.

Efficient deployment of small language models (SLMs) is essential for numerous real-world applications with stringent latency constraints. While previous work on SLM design has primarily focused on reducing the number of parameters to achieve parameter-optimal SLMs, parameter efficiency does not necessarily translate into proportional real-device speed-ups. This work aims to identify the key determinants of SLMs' real-device latency and offer generalizable principles and methodologies for SLM design and training when real-device latency is the primary consideration. Specifically, we identify two central architectural factors: depth-width ratios and operator choices. The former is crucial for small-batch-size latency, while the latter affects both latency and large-batch-size throughput. In light of this, we first study latency-optimal depth-width ratios, with the key finding that although deep-thin models generally achieve better accuracy under the same parameter budget, they may not lie on the accuracy-latency trade-off frontier. Next, we explore emerging efficient attention alternatives to evaluate their potential as candidate building operators. Using the identified promising operators, we construct an evolutionary search framework to automatically discover latency-optimal combinations of these operators within hybrid SLMs, thereby advancing the accuracy-latency frontier. In addition to architectural improvements, we further enhance SLM training using a weight normalization technique that enables more effective weight updates and improves final convergence. Combining these methods, we introduce a new family of hybrid SLMs, called Nemotron-Flash, which significantly advances the accuracy-efficiency frontier of state-of-the-art SLMs, e.g., achieving over +5.5% average accuracy, 1.3x/1.9x lower latency, and 18.7x/45.6x higher throughput compared to Qwen3-1.7B/0.6B, respectively.

For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency. Existing methods on hardware-aware NAS collect a large number of samples (e.g., accuracy and latency) from a target device, either builds a lookup table or a latency estimator. However, such approach is impractical in real-world scenarios as there exist numerous devices with different hardware specifications, and collecting samples from such a large number of devices will require prohibitive computational and monetary cost. To overcome such limitations, we propose Hardware-adaptive Efficient Latency Predictor (HELP), which formulates the device-specific latency estimation problem as a meta-learning problem, such that we can estimate the latency of a model's performance for a given task on an unseen device with a few samples. To this end, we introduce novel hardware embeddings to embed any devices considering them as black-box functions that output latencies, and meta-learn the hardware-adaptive latency predictor in a device-dependent manner, using the hardware embeddings. We validate the proposed HELP for its latency estimation performance on unseen platforms, on which it achieves high estimation performance with as few as 10 measurement samples, outperforming all relevant baselines. We also validate end-to-end NAS frameworks using HELP against ones without it, and show that it largely reduces the total time cost of the base NAS method, in latency-constrained settings. Code is available at https://github.com/HayeonLee/HELP.

Many applications must provide low-latency LLM service to users or risk unacceptable user experience. However, over-provisioning resources to serve fluctuating request patterns is often prohibitively expensive. In this work, we present a best-effort serving system that employs deep reinforcement learning to adjust service quality based on the task distribution and system load. Our best-effort system can maintain availability with over 10x higher client request rates, serves above 96% of peak performance 4.1x more often, and serves above 98% of peak performance 2.3x more often than static serving on unpredictable workloads. Our learned router is robust to shifts in both the arrival and task distribution. Compared to static serving, learned best-effort serving allows for cost-efficient serving through increased hardware utility. Additionally, we argue that learned best-effort LLM serving is applicable in wide variety of settings and provides application developers great flexibility to meet their specific needs.

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a latency-aware evaluation of representative TTS methods, we demonstrate that a compute-optimal TTS does not always result in the lowest latency in scenarios where latency is critical. To address this gap and achieve latency-optimal TTS, we propose two key approaches by optimizing the concurrency configurations: (1) branch-wise parallelism, which leverages multiple concurrent inference branches, and (2) sequence-wise parallelism, enabled by speculative decoding. By integrating these two approaches and allocating computational resources properly to each, our latency-optimal TTS enables a 32B model to reach 82.3% accuracy on MATH-500 within 1 minute and a smaller 3B model to achieve 72.4% within 10 seconds. Our work emphasizes the importance of latency-aware TTS and demonstrates its ability to deliver both speed and accuracy in latency-sensitive scenarios.

Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like document summarization. The existing deployment model, which dedicates machines to each workload, simplifies SLO management but often leads to poor resource utilization. This paper introduces HyGen, an interference-aware LLM serving system that enables efficient co-location of online and offline workloads while preserving latency requirements. HyGen incorporates two key innovations: (1) performance control mechanisms, including a latency predictor to estimate batch execution time and an SLO-aware profiler to quantify latency interference, and (2) SLO-aware offline scheduling policies that maximize serving throughput and prevent starvation, without compromising online serving latency. Our evaluation on production workloads shows that HyGen achieves up to 3.87x overall throughput and 5.84x offline throughput gains over online and hybrid serving baselines, respectively, while strictly satisfying latency SLOs.

Scheduling policies in large-scale Automatic Speech Recognition (ASR) serving pipelines play a key role in determining end-to-end (E2E) latency. Yet, widely used serving engines rely on first-come-first-served (FCFS) scheduling, which ignores variability in request duration and leads to head-of-line blocking under workload drift. We show that audio duration is an accurate proxy for job processing time in ASR models such as Whisper, and use this insight to enable duration-aware scheduling. We integrate two classical algorithms, Shortest Job First (SJF) and Highest Response Ratio Next (HRRN), into vLLM and evaluate them under realistic and drifted workloads. On LibriSpeech test-clean, compared to baseline, SJF reduces median E2E latency by up to 73% at high load, but increases 90th-percentile tail latency by up to 97% due to starvation of long requests. HRRN addresses this trade-off: it reduces median E2E latency by up to 28% while bounding tail-latency degradation to at most 24%. These gains persist under workload drift, with no throughput penalty and <0.1\,ms scheduling overhead per request.

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive requests emphasizing per-token latency in streaming chat, deadline-sensitive requests requiring rapid full responses to trigger external tools, and compound requests with evolving dependencies across multiple LLM calls. Despite-or perhaps, because of-this workload diversity and unpredictable request information (e.g., response lengths and dependencies), existing request schedulers have focused on aggregate performance, unable to ensure application-level SLO needs. This paper presents JITServe, the first SLO-aware LLM serving system designed to maximize service goodput (e.g., the number of tokens meeting request SLOs) across diverse workloads. JITServe novelly schedules requests using imprecise request information and gradually relaxes this conservatism by refining request information estimates as generation progresses. It applies a grouped margin goodput maximization algorithm to allocate just enough serving bandwidth to satisfy each request's SLO just-in-time (JIT), maximizing residual capacity for others, while deciding the composition of requests in a batch to maximize efficiency and goodput with provable guarantees. Our evaluation across diverse realistic workloads, including chat, deep research, and agentic pipelines, shows that JITServe improves service goodput by 1.4x-6.3x, alternatively achieving 28.5%-83.2% resource savings, compared to state-of-the-art designs.

Realistic evaluation of LLM serving systems requires online workloads, dynamic arrivals, queueing, and the serving engine's local scheduling for execution batching, but running such experiments on GPUs is expensive. Existing simulators reduce this cost, but often operate offline or in time-warped mode, re-implement serving-engine schedulers, or require accurate operator/kernel-level latency models. We present LLM-Emu, a serving-native emulator for vLLM that preserves the production HTTP, scheduling, KV-cache, and output-processing paths while replacing only GPU forward execution with profile-sampled latency and synthetic output tokens. Tested on two different GPUs, four model variants, two model families, two attention backends, and both Poisson and bursty ShareGPT workloads, LLM-Emu closely tracks real vLLM serving behavior: TPOT and ITL stay within 4.8% absolute error, E2E latency within 5.3%, and output throughput within 1.9%; TTFT is less stable, with maximum error 10.4%, reflecting its sensitivity to admission and queue state. These results suggest that lightweight, serving-native emulation can support practical online experimentation for LLM-serving systems. LLM-Emu is open sourced at https://github.com/AKafakA/llm-emu.

Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation. This regime hides a dangerous failure mode. On a real full-duplex stack, sustained load does not degrade serving gracefully: it falls off a cliff, jumping in one step from milliseconds per frame to a stalled engine when accumulated session state exhausts the KV pool. The collapse is metastable -- identical five-minute runs collapse or survive on run-to-run variance -- and silent: latency and deadline-miss metrics read healthy throughout. We show one move restores both stability and observability: bound each session's resident state, and latency starts telling the truth. Metronome's in-engine KV window eliminates the collapse (0/20 vs. 14/20 runs across two batches) and turns per-frame latency into a monotone load signal, on which an online admission controller discovers the schedulable concurrency; without the window, the identical controller over-admits into the wall. A first-order model predicts the collapse time within a few percent on the headline model, and a quality probe validates the bound's design by ablation: the window alone is quality-free in turn-based decoding, and its few pinned attention-sink tokens are what keep free-running generation healthy. Everything is measured end-to-end on real audio, across four interaction models on one GPU.

Simultaneous speech-to-text translation (SimulST) systems have to balance translation quality with latency--the delay between speech input and the translated output. While quality evaluation is well established, accurate latency measurement remains a challenge. Existing metrics often produce inconsistent or misleading results, especially in the widely used short-form setting, where speech is artificially presegmented. In this paper, we present the first comprehensive analysis of SimulST latency metrics across language pairs, systems, and both short- and long-form regimes. We uncover a structural bias in current metrics related to segmentation that undermines fair and meaningful comparisons. To address this, we introduce YAAL (Yet Another Average Lagging), a refined latency metric that delivers more accurate evaluations in the short-form regime. We extend YAAL to LongYAAL for unsegmented audio and propose SoftSegmenter, a novel resegmentation tool based on word-level alignment. Our experiments show that YAAL and LongYAAL outperform popular latency metrics, while SoftSegmenter enhances alignment quality in long-form evaluation, together enabling more reliable assessments of SimulST systems.

Real-time spoken dialogue systems face a fundamental tension between latency and response quality. End-to-end speech-to-speech (S2S) models respond immediately and naturally handle turn-taking, backchanneling, and interruption, but produce semantically weaker outputs. Cascaded pipelines (ASR -> LLM) deliver stronger responses at the cost of latency that grows with model size. We present RelayS2S, a hybrid architecture that runs two paths in parallel upon turn detection. The fast path -- a duplex S2S model -- speculatively drafts a short response prefix that is streamed immediately to TTS for low-latency audio onset, while continuing to monitor live audio events. The slow path -- a cascaded ASR -> LLM pipeline -- generates a higher-quality continuation conditioned on the committed prefix, producing a seamless utterance. A lightweight learned verifier gates the handoff, committing the prefix when appropriate or falling back gracefully to the slow path alone. Experiments show that RelayS2S achieves P90 onset latency comparable to the S2S model while retaining 99% cascaded response quality in average score, with benefits growing as the slow-path model scales. Because the prefix handoff requires no architectural modification to either component, RelayS2S serves as a lightweight, drop-in addition to existing cascaded pipelines. Our code and data are publicly available at: https://github.com/mailong25/relays2s

Google's congestion control (GCC) has become a cornerstone for real-time video and audio communication, yet its performance remains fragile in emerging Low Earth Orbit (LEO) networks. Sparse direct-to-device constellations offer longer duration links and reduced handover frequency compared to dense deployments, presenting a unique opportunity for high-quality real-time communication (RTC) in environments with limited terrestrial network infrastructure. In this paper, we study the behavior of videoconferencing systems in sparse LEO constellations. We observe that video quality degrades due to inherent delays and network instability introduced by the high altitude and rapid movement of LEO satellites, with these effects exacerbated by WebRTC's conventional ``one-size-fits-all'' sender-side pacing queue management. To boost RTC performance, we introduce a data-driven queue management mechanism that adapts the maximum pacing queue capacity based on predicted handover activity. Specifically, our approach employs shorter queue limits during stable, no-handover phases to prioritize low latency communication, and preemptively increases pacing queue capacity when entering periods of increased handover activity to absorb disruptions. Our method yields up to 3x improvements in video bitrate and reduces freeze rate by 62% compared to default WebRTC.

There have been significant advances in deep learning for music demixing in recent years. However, there has been little attention given to how these neural networks can be adapted for real-time low-latency applications, which could be helpful for hearing aids, remixing audio streams and live shows. In this paper, we investigate the various challenges involved in adapting current demixing models in the literature for this use case. Subsequently, inspired by the Hybrid Demucs architecture, we propose the Hybrid Spectrogram Time-domain Audio Separation Network HS-TasNet, which utilises the advantages of spectral and waveform domains. For a latency of 23 ms, the HS-TasNet obtains an overall signal-to-distortion ratio (SDR) of 4.65 on the MusDB test set, and increases to 5.55 with additional training data. These results demonstrate the potential of efficient demixing for real-time low-latency music applications.

Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limiting their scalability and usability in time-sensitive scenarios. Most existing approaches primarily optimize task performance and inference cost, and explicitly or implicitly assume sequential execution, making them less optimal for controlling latency under parallel execution. In this work, we investigate learning-based orchestration of multi-agent systems with explicit latency supervision under parallel execution. We propose Latency-Aware Multi-agent System (LAMaS), a latency-aware multi-agent orchestration framework that enables parallel execution and explicitly optimizes the critical execution path, allowing the controller to construct execution topology graphs with lower latency under parallel execution. Our experiments show that our approach reduces critical path length by 38-46% compared to the state-of-the-art baseline for multi-agent architecture search across multiple benchmarks, while maintaining or even improving task performance. These results highlight the importance of explicitly optimizing latency under parallel execution when designing efficient multi-agent systems. The code is available at https://github.com/xishi404/LAMaS

Different real-time speech applications impose distinct latency budgets, often requiring separately trained enhancement models for each scenario. In this paper, we propose a one-for-all, real-time universal speech enhancement model that provides explicit control over both algorithmic and computational latency. Algorithmic latency is flexibly adjusted via configurable look-ahead frames. To avoid learning inefficiency caused by varying padding configurations, we introduce parallel convolutional layers corresponding to different look-ahead settings. Computational latency is controlled through an early-exit mechanism, enabling inference at different network depths. To narrow the performance gap between specialized and flexible models, we propose a two-stage training strategy with a shared-to-multiple decoder transition. Overall, the proposed framework enables a single model to be deployed across diverse latency budgets without retraining separate models.

Recent advancements in large language models (LLMs) and multimodal speech-text models have laid the groundwork for seamless voice interactions, enabling real-time, natural, and human-like conversations. Previous models for voice interactions are categorized as native and aligned. Native models integrate speech and text processing in one framework but struggle with issues like differing sequence lengths and insufficient pre-training. Aligned models maintain text LLM capabilities but are often limited by small datasets and a narrow focus on speech tasks. In this work, we introduce MinMo, a Multimodal Large Language Model with approximately 8B parameters for seamless voice interaction. We address the main limitations of prior aligned multimodal models. We train MinMo through multiple stages of speech-to-text alignment, text-to-speech alignment, speech-to-speech alignment, and duplex interaction alignment, on 1.4 million hours of diverse speech data and a broad range of speech tasks. After the multi-stage training, MinMo achieves state-of-the-art performance across various benchmarks for voice comprehension and generation while maintaining the capabilities of text LLMs, and also facilitates full-duplex conversation, that is, simultaneous two-way communication between the user and the system. Moreover, we propose a novel and simple voice decoder that outperforms prior models in voice generation. The enhanced instruction-following capabilities of MinMo supports controlling speech generation based on user instructions, with various nuances including emotions, dialects, and speaking rates, and mimicking specific voices. For MinMo, the speech-to-text latency is approximately 100ms, full-duplex latency is approximately 600ms in theory and 800ms in practice. The MinMo project web page is https://funaudiollm.github.io/minmo, and the code and models will be released soon.

We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use. Unlike prior work, our dataset consists entirely of real human audio annotated for five disfluency categories, paired with scenarios requiring chained API calls across four task domains. We evaluate six model configurations -- GPT-Realtime, Gemini Live 2.5, Gemini Live 3.1, Grok, Ultravox v0.7, and a traditional Cascaded pipeline (WhisperrightarrowGPT-4orightarrowTTS) -- across accuracy, latency, and turn-taking dimensions. GPT-Realtime leads on Pass@1 (0.600) and interruption avoidance (13.5\%); Gemini Live 3.1 achieves the fastest latency (4.25~s) but the lowest turn-take rate (78.0\%); and the Cascaded baseline, despite a perfect turn-take rate, incurs the highest latency (10.12~s). Across all systems, self-correction handling and multi-step reasoning under hard scenarios remain the most consistent failure modes.

In production large language model (LLM) deployments, high API availability guarantees do not equate to conversational continuity. When a primary provider experiences an outage or strict rate-limiting, naive stateless failover mechanisms successfully maintain uptime but silently discard conversation history, severely disrupting the user experience. To rigorously quantify and resolve this failure mode, we introduce two novel metrics: Continuity Preservation Rate (CPR) and Continuity Latency Overhead (CLO). We propose a stateful, multi-provider proxy architecture utilizing a History-Forwarding strategy to seamlessly reconstruct conversational state across heterogeneous LLM endpoints during failover events. Furthermore, we release continuity-bench, https://github.com/Vishal-sys-code/continuity-bench, an open evaluation harness designed to stress-test context preservation under high-concurrency provider failure conditions. Our empirical evaluation (N=750 failover events) demonstrates that our stateful proxy achieves a 99.20\% CPR [95\% CI: 98.27\%, 99.63\%], cleanly transferring deep conversational context to fallback providers, compared to a near-0\% preservation rate for standard stateless architectures. Finally, we characterize failover latency distributions, identifying the critical necessity of asynchronous exponential backoff with jitter to prevent cascading retry storms against strict-limit fallback APIs. Our results provide a principled foundation for building robust, state-preserving multi-model inference systems.

Fluid voice-to-voice interaction requires reliable and low-latency detection of when a user has finished speaking. Traditional audio-silence end-pointers add hundreds of milliseconds of delay and fail under hesitations or language-specific phenomena. We present, to our knowledge, the first systematic study of Thai text-only end-of-turn (EOT) detection for real-time agents. We compare zero-shot and few-shot prompting of compact LLMs to supervised fine-tuning of lightweight transformers. Using transcribed subtitles from the YODAS corpus and Thai-specific linguistic cues (e.g., sentence-final particles), we formulate EOT as a binary decision over token boundaries. We report a clear accuracy-latency tradeoff and provide a public-ready implementation plan. This work establishes a Thai baseline and demonstrates that small, fine-tuned models can deliver near-instant EOT decisions suitable for on-device agents.

We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While end-to-end speech-to-speech models may ultimately provide the best latency for voice agents, fully self-hosted end-to-end solutions are not yet available. We evaluate the closest candidate, Qwen3-Omni, across three configurations: its cloud-only DashScope Realtime API achieves sim702ms audio-to-audio latency with streaming, but is not self-hostable; its local vLLM deployment supports only the Thinker (text generation from audio, 516ms), not the Talker (audio synthesis); and its local Transformers deployment runs the full pipeline but at sim146s -- far too slow for realtime. The cascaded streaming pipeline (STT rightarrow LLM rightarrow TTS) therefore remains the practical architecture for self-hosted realtime voice agents, and the focus of this tutorial. We build a complete voice agent using Deepgram (streaming STT), vLLM-served LLMs with function calling (streaming text generation), and ElevenLabs (streaming TTS), achieving a measured time-to-first-audio of 755ms (best case 729ms) with full function calling support. We release the full codebase as a 9-chapter progressive tutorial with working, tested code for every component.

Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM reasoning to mitigate uncertainties and reduce potential errors. However, existing research predominantly focuses on reasoning performance, often neglecting the efficiency of agentic systems. In this work, we present a comprehensive empirical study that identifies efficiency bottlenecks in web-interactive agentic systems. We decompose end-to-end latency into two primary components: LLM API latency and web environment latency. We conduct a comprehensive empirical study across 15 models and 5 providers to demonstrate high variability in API-based agentic systems. We observe that web environment latency can contribute as much as 53.7% to the overall latency in a web-based agentic system. To improve latency, we propose SpecCache, a caching framework augmented with speculative execution that can reduce web environment overhead. Extensive evaluations on two standard benchmarks show that our approach improves the cache hit rate by up to 58x compared to a random caching strategy, while reducing web environment overhead by up to 3.2x, without degrading agentic system performance.

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual sub-procedures, e.g. local inference and communication, however, there is no comprehensive framework that provides a holistic system view for optimizing LLM serving in an end-to-end manner. In this work, we conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. Our analysis reveals that a comprehensive LLM serving endpoint must address a series of efficiency bottlenecks that extend beyond LLM inference. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving. Our extensive experiments reveal that with 64 concurrent requests, ScaleLLM achieves a 4.3x speed up over vLLM and outperforms state-of-the-arts with 1.5x higher throughput.

Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference systems employ iteration-level first-come-first-served scheduling, causing head-of-line blocking when BE jobs delay LS jobs. We introduce QLLM, a novel inference system designed for Mixture of Experts (MoE) models, featuring a fine-grained, priority-aware preemptive scheduler. QLLM enables expert-level preemption, deferring BE job execution while minimizing LS time-to-first-token (TTFT). Our approach removes iteration-level scheduling constraints, enabling the scheduler to preempt jobs at any layer based on priority. Evaluations on an Nvidia A100 GPU show that QLLM significantly improves performance. It reduces LS TTFT by an average of 65.5times and meets the SLO at up to 7 requests/sec, whereas the baseline fails to do so under the tested workload. Additionally, it cuts LS turnaround time by up to 12.8times without impacting throughput. QLLM is modular, extensible, and seamlessly integrates with Hugging Face MoE models.

This study introduces CUPID, a novel approach to session-based reciprocal recommendation systems designed for a real-time one-on-one social discovery platform. In such platforms, low latency is critical to enhance user experiences. However, conventional session-based approaches struggle with high latency due to the demands of modeling sequential user behavior for each recommendation process. Additionally, given the reciprocal nature of the platform, where users act as items for each other, training recommendation models on large-scale datasets is computationally prohibitive using conventional methods. To address these challenges, CUPID decouples the time-intensive user session modeling from the real-time user matching process to reduce inference time. Furthermore, CUPID employs a two-phase training strategy that separates the training of embedding and prediction layers, significantly reducing the computational burden by decreasing the number of sequential model inferences by several hundredfold. Extensive experiments on large-scale Azar datasets demonstrate CUPID's effectiveness in a real-world production environment. Notably, CUPID reduces response latency by more than 76% compared to non-asynchronous systems, while significantly improving user engagement.

Despite their remarkable success in complex tasks propelling widespread adoption, large language-model-based agents still face critical deployment challenges due to prohibitive latency and inference costs. While recent work has explored various methods to accelerate inference, existing approaches suffer from significant limitations: they either fail to preserve performance fidelity, require extensive offline training of router modules, or incur excessive operational costs. Moreover, they provide minimal user control over the tradeoff between acceleration and other performance metrics. To address these gaps, we introduce Dynamic Speculative Planning (DSP), an asynchronous online reinforcement learning framework that provides lossless acceleration with substantially reduced costs without requiring additional pre-deployment preparation. DSP explicitly optimizes a joint objective balancing end-to-end latency against dollar cost, allowing practitioners to adjust a single parameter that steers the system toward faster responses, cheaper operation, or any point along this continuum. Experiments on two standard agent benchmarks demonstrate that DSP achieves comparable efficiency to the fastest lossless acceleration method while reducing total cost by 30% and unnecessary cost up to 60%. Our code and data are available through https://github.com/guanyilin428/Dynamic-Speculative-Planning.

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster. However existing scheduling algorithms treat LLM workloads as monolithic jobs without considering the distinct characteristics of the two phases in each workload. This leads to sub-optimal scheduling and increased response latency. In this work, we propose a heuristic-guided reinforcement learning-based intelligent router for data-driven and workload-aware scheduling. Our router leverages a trainable response-length predictor, and a novel formulation for estimating the impact of mixing different workloads to schedule queries across LLM instances and achieve over 11\% lower end-to-end latency than existing approaches.

Differentiable neural architecture search methods became popular in recent years, mainly due to their low search costs and flexibility in designing the search space. However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware. This paper deals with this problem by adding a differentiable latency loss term into optimization, so that the search process can tradeoff between accuracy and latency with a balancing coefficient. The core of latency prediction is to encode each network architecture and feed it into a multi-layer regressor, with the training data which can be easily collected from randomly sampling a number of architectures and evaluating them on the hardware. We evaluate our approach on NVIDIA Tesla-P100 GPUs. With 100K sampled architectures (requiring a few hours), the latency prediction module arrives at a relative error of lower than 10%. Equipped with this module, the search method can reduce the latency by 20% meanwhile preserving the accuracy. Our approach also enjoys the ability of being transplanted to a wide range of hardware platforms with very few efforts, or being used to optimizing other non-differentiable factors such as power consumption.

Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we present LiveSpeech - a fully autoregressive language model-based approach for zero-shot text-to-speech, enabling low-latency streaming of the output audio. To allow multiple token prediction within a single decoding step, we propose (1) using adaptive codebook loss weights that consider codebook contribution in each frame and focus on hard instances, and (2) grouping codebooks and processing groups in parallel. Experiments show our proposed models achieve competitive results to state-of-the-art baselines in terms of content accuracy, speaker similarity, audio quality, and inference speed while being suitable for low-latency streaming applications.

Latency-critical speech applications (e.g., live transcription, voice commands, and real-time translation) demand low time-to-first-token (TTFT) and high transcription accuracy, particularly on resource-constrained edge devices. Full-attention Transformer encoders remain a strong accuracy baseline for automatic speech recognition (ASR) because every frame can directly attend to every other frame, which resolves otherwise locally ambiguous acoustics using distant lexical context. However, this global dependency incurs quadratic complexity in sequence length, inducing an inherent "encode-the-whole-utterance" latency profile. For streaming use cases, this causes TTFT to grow linearly with utterance length as the encoder must process the entire prefix before any decoder token can be emitted. To better meet the needs of on-device, streaming ASR use cases we introduce Moonshine v2, an ergodic streaming-encoder ASR model that employs sliding-window self-attention to achieve bounded, low-latency inference while preserving strong local context. Our models achieve state of the art word error rates across standard benchmarks, attaining accuracy on-par with models 6x their size while running significantly faster. These results demonstrate that carefully designed local attention is competitive with the accuracy of full attention at a fraction of the size and latency cost, opening new possibilities for interactive speech interfaces on edge devices.

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming (online or real-time) transcription, due to limitations in their architecture and training methodology. We propose a method to turn the transformer encoder-decoder model into a low-latency streaming model that is careless about future context. We present an analysis explaining why it is not straightforward to convert an encoder-decoder transformer to a low-latency streaming model. Our proposed method modifies the existing (non-causal) encoder to a causal encoder by fine-tuning both the encoder and decoder using Low-Rank Adaptation (LoRA) and a weakly aligned dataset. We then propose an updated inference mechanism that utilizes the fine-tune causal encoder and decoder to yield greedy and beam-search decoding, and is shown to be locally optimal. Experiments on low-latency chunk sizes (less than 300 msec) show that our fine-tuned model outperforms existing non-fine-tuned streaming approaches in most cases, while using a lower complexity. Additionally, we observe that our training process yields better alignment, enabling a simple method for extracting word-level timestamps. We release our training and inference code, along with the fine-tuned models, to support further research and development in streaming ASR.

ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language model inference efficiency by routing each request to an appropriate fixed inference mode. Instead of relying on one static serving configuration, the system selects among FP16, quantized modes, speculative decoding, and hybrid modes such as GPTQ plus prefix caching and INT8 plus continuous batching using cheap workload-level features. We evaluate ModeSwitch-LLM on Meta-Llama-3.1-8B-Instruct served on a single NVIDIA A100 GPU. On deployment-style synthetic workloads, the online controller achieves a 2.10x mean latency speedup over FP16 and a 0.48x mean energy ratio, corresponding to 51.7% lower energy per token. On automatic benchmarks used as a quality gate, accuracy remains close to FP16 with a mean delta of +0.17 percentage points. We also evaluate lightweight learned routers, but find that they do not clearly outperform the rule-based controller because they add routing overhead and more often select modes that violate quality, energy, or memory constraints. These results show that simple request-aware routing can recover substantial efficiency from existing inference modes without retraining the model or changing its architecture.

We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-causal attention for incremental streaming. Unlike cascaded interactive systems that rely on separate VAD, ASR, language, TTS, audio-driven animation, or video-generation modules, Wan-Streamer does not rely on external language, speech, avatar, or video-generation modules: perception, reasoning, generation, response timing, turn management, and cross-modal synchronization are learned jointly within one unified model, reducing pipeline latency and error accumulation. To support natural audio-visual responsiveness, we redesign the entire stack around streamability, including causal encoders, causal decoders, block-causal attention, and low-latency multimodal token scheduling, enabling streaming units as short as 160 ms at 25 fps. Wan-Streamer achieves approximately 200 ms model-side response latency and approximately 550 ms total interaction latency when combined with 350 ms bidirectional network latency, supporting sub-second duplex audio-visual communication. These results position Wan-Streamer as a unified, end-to-end, multimodal interactive foundation model for low-latency streaming interaction.

We adapt the architectures of previous audio manipulation and generation neural networks to the task of real-time any-to-one voice conversion. Our resulting model, LLVC (Low-latency Low-resource Voice Conversion), has a latency of under 20ms at a bitrate of 16kHz and runs nearly 2.8x faster than real-time on a consumer CPU. LLVC uses both a generative adversarial architecture as well as knowledge distillation in order to attain this performance. To our knowledge LLVC achieves both the lowest resource usage as well as the lowest latency of any open-source voice conversion model. We provide open-source samples, code, and pretrained model weights at https://github.com/KoeAI/LLVC.

In simultaneous speech translation (SimulST), finding the best trade-off between high translation quality and low latency is a challenging task. To meet the latency constraints posed by the different application scenarios, multiple dedicated SimulST models are usually trained and maintained, generating high computational costs. In this paper, motivated by the increased social and environmental impact caused by these costs, we investigate whether a single model trained offline can serve not only the offline but also the simultaneous task without the need for any additional training or adaptation. Experiments on en->{de, es} indicate that, aside from facilitating the adoption of well-established offline techniques and architectures without affecting latency, the offline solution achieves similar or better translation quality compared to the same model trained in simultaneous settings, as well as being competitive with the SimulST state of the art.

Training of large language models (LLMs) is typically distributed across a large number of accelerators to reduce training time. Since internal states and parameter gradients need to be exchanged at each and every single gradient step, all devices need to be co-located using low-latency high-bandwidth communication links to support the required high volume of exchanged bits. Recently, distributed algorithms like DiLoCo have relaxed such co-location constraint: accelerators can be grouped into ``workers'', where synchronizations between workers only occur infrequently. This in turn means that workers can afford being connected by lower bandwidth communication links without affecting learning quality. However, in these methods, communication across workers still requires the same peak bandwidth as before, as the synchronizations require all parameters to be exchanged across all workers. In this paper, we improve DiLoCo in three ways. First, we synchronize only subsets of parameters in sequence, rather than all at once, which greatly reduces peak bandwidth. Second, we allow workers to continue training while synchronizing, which decreases wall clock time. Third, we quantize the data exchanged by workers, which further reduces bandwidth across workers. By properly combining these modifications, we show experimentally that we can distribute training of billion-scale parameters and reach similar quality as before, but reducing required bandwidth by two orders of magnitude.

In large-scale reinforcement learning (RL) systems with decoupled Trainer-Rollout execution, the Trainer must regularly synchronize policy weights to the Rollout side to limit policy staleness. When inter-node bandwidth is abundant, such synchronization is usually only a small fraction of end-to-end cost. As model size grows, however, the communication demand rises rapidly. In bandwidth-constrained or network-variable deployments -- for example, cross-datacenter or cross-cluster settings, heterogeneous resource pools, and online RL -- weight synchronization can become a dominant bottleneck for throughput and tail latency. We observe that, in mainstream large-model RL training, the locations where parameters actually change are highly sparse at the element level (often 99%+ sparsity). Building on this observation, we propose and implement SparseRL-Sync, which replaces full-weight transfers with a lossless sparse update payload (indices and values) that can be exactly reconstructed on the inference side, thereby preserving 100% fidelity. Under a simplified cost model, sparse synchronization reduces the per-update communication volume from S to approximately S/X; with 99% sparsity (X ~ 100), this yields about a 100x reduction in transmitted data. Combined with appropriate bucketing, SparseRL-Sync also reduces launch and control-plane overhead, significantly improving scalability and end-to-end efficiency in bandwidth-limited and highly asynchronous RL settings.

The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests that meet their Service Level Objectives (SLOs), particularly for Time To First Token (TTFT) and Time Between Tokens (TBT). However, existing systems often prioritize one metric at the cost of the other. We present Ascendra, an LLM serving system designed to meet both TTFT and TBT SLOs simultaneously. The core insight behind Ascendra is that a request's urgency evolves as it approaches its deadline. To leverage this, Ascendra partitions GPU resources into two types of instances: low-priority and high-priority. Low-priority instances maximize throughput by processing requests out of arrival order, but at the risk of request starvation. To address this, Ascendra employs a performance model to predict requests at risk of missing their SLOs and proactively offloads them to high-priority instances. High-priority instances are optimized for low-latency execution and handle urgent requests nearing their deadlines. This partitioned architecture enables Ascendra to effectively balance high throughput and low latency. Extensive evaluation shows that Ascendra improves system throughput by up to 1.7x compared to vLLM and Sarathi-Serve while meeting both TTFT and TBT SLOs.

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a disaggregated system where the two phases are disaggregated to different GPUs. The design of the disaggregated system addresses the latency interference and sophisticated scheduling issues in the unified system but leads to storage challenges including 1) replicated weights for both phases that prevent flexible deployment, 2) KV cache transfer overhead between the two phases, 3) storage imbalance that causes substantial wasted space of the GPU capacity, and 4) suboptimal resource adjustment arising from the difficulties in migrating KV cache. Such storage inefficiency delivers poor serving performance under high request rates. In this paper, we identify that the advantage of the disaggregated system lies in the disaggregated computation, i.e., partitioning the computational resource to enable the asynchronous computation of two phases. Thus, we propose a novel LLM serving system, semi-PD, characterized by disaggregated computation and unified storage. In semi-PD, we introduce a computation resource controller to achieve disaggregated computation at the streaming multi-processor (SM) level, and a unified memory manager to manage the asynchronous memory access from both phases. semi-PD has a low-overhead resource adjustment mechanism between the two phases, and a service-level objective (SLO) aware dynamic partitioning algorithm to optimize the SLO attainment. Compared to state-of-the-art systems, semi-PD maintains lower latency at higher request rates, reducing the average end-to-end latency per request by 1.27-2.58x on DeepSeek series models, and serves 1.55-1.72x more requests adhering to latency constraints on Llama series models.

As large-scale multi-agent systems evolve, the communication protocol layer has become a critical yet under-evaluated factor shaping performance and reliability. Despite the existence of diverse protocols (A2A, ACP, ANP, Agora, etc.), selection is often intuition-driven and lacks standardized guidance. We introduce ProtocolBench, a benchmark that systematically compares agent protocols along four measurable axes: task success, end-to-end latency, message or byte overhead, and robustness under failures. On ProtocolBench, protocol choice significantly influences system behavior. In the Streaming Queue scenario, overall completion time varies by up to 36.5% across protocols, and mean end-to-end latency differs by 3.48 s. Under Fail-Storm Recovery, resilience also differs consistently across protocols. Beyond evaluation, we present ProtocolRouter, a learnable protocol router that selects per-scenario (or per-module) protocols from requirement and runtime signals. ProtocolRouter reduces Fail-Storm recovery time by up to 18.1% versus the best single-protocol baseline, and achieves scenario-specific gains such as higher success in GAIA. We also release ProtocolRouterBench to standardize protocol evaluation and improve reliability at scale.

Full-duplex dialog models are designed to listen and speak simultaneously with rapid responses to fast-changing user input. Among existing approaches, native full-duplex models merges different channels (e.g. listen and speak) in a single time step, overcoming the high response latency inherent to time-division multiplexing time-division multiplexing (TDM) alternatives. Yet, a key challenge remains: aligning textual monologues with audio streams that operate at different bitrates. The prevailing solution relies on word-level alignment, but this can degrade the language ability of large pre-trained models. Moreover, it requires highly accurate timestamps for every token, which introduces cascading errors and increases pre-processing costs. In this paper, we propose textual monologues in continuous tokens sequence, namely "natural" monologues, which mimics humanoid cognitive behavior in dialogs. For temporal alignment, we alternate the position of the natural monologue - leading or trailing the audio - across different training stages. This "dual" training paradigm proves highly effective in building FLM-Audio, our 7B spoken dialog model that demonstrates superior responsiveness, duplexity, and chatting experiences, as confirmed by experimental results.

The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements, especially for workloads with long prompts. This paper introduces DeepSpeed-FastGen, a system that employs Dynamic SplitFuse, a novel prompt and generation composition strategy, to deliver up to 2.3x higher effective throughput, 2x lower latency on average, and up to 3.7x lower (token-level) tail latency, compared to state-of-the-art systems like vLLM. We leverage a synergistic combination of DeepSpeed-MII and DeepSpeed-Inference to provide an efficient and easy-to-use serving system for LLMs. DeepSpeed-FastGen's advanced implementation supports a range of models and offers both non-persistent and persistent deployment options, catering to diverse user scenarios from interactive sessions to long-running applications. We present a detailed benchmarking methodology, analyze the performance through latency-throughput curves, and investigate scalability via load balancing. Our evaluations demonstrate substantial improvements in throughput and latency across various models and hardware configurations. We discuss our roadmap for future enhancements, including broader model support and new hardware backends. The DeepSpeed-FastGen code is readily available for community engagement and contribution.

Increasingly, LLM inference services proxy client requests to engine replicas distributed globally. Load-balancing policies must jointly account for factors including KV-cache locality, replica load, and variable network latency when optimizing for metrics like latency and TTFT. However, existing systems only evaluate a subset of these factors in their cost model, leading to uneven concentrations of load and KV-cache across replicas. We present GORGO, a proxy architecture that holistically factors network latency, prefill cost, and queueing delay using tunable parameters. Since open-source chat datasets such as LMSYS-Chat1M and WildChat-4.8M lack long-context, high prefix-reuse data, we release a synthetic dataset, ART-Chat-2.5M, from long-context production metadata. On a tuning window from ART-Chat-2.5M, evolutionary strategies guide the GORGO policy's parameters to directly optimize p95 TTFT. During held-out evaluation windows, we fix the parameter values learned from tuning and improve p95 TTFT by 6.9-15.5% and p95 end-to-end (E2E) latency by 14.3-30.9% over baseline load-balancing policies such as simple session affinity and prefix-cache. The code and ART-Chat-2.5M dataset can be found at https://github.com/Arcadia-Research-Team/GORGO.

In this paper, we introduce a novel low-latency inference framework for large language models (LLMs) inference which enables LLMs to perform inferences with incomplete prompts. By reallocating computational processes to prompt input phase, we achieve a substantial reduction in latency, thereby significantly enhancing the interactive experience for users of LLMs. The framework adeptly manages the visibility of the streaming prompt to the model, allowing it to infer from incomplete prompts or await additional prompts. Compared with traditional inference methods that utilize complete prompts, our approach demonstrates an average reduction of 59% in response latency on the MMLU-Pro dataset, while maintaining comparable accuracy. Additionally, our framework facilitates collaborative inference and output across different models. By employing an LLM for inference and a small language model (SLM) for output, we achieve an average 68% reduction in response latency, alongside a 5.5% improvement in accuracy on the MMLU-Pro dataset compared with the SLM baseline. For long prompts exceeding 20 sentences, the response latency can be reduced by up to 93%.

Current Cyber-Physical Systems (CPS) integrated with Digital Twin (DT) technology face critical limitations in achieving real-time performance for mission-critical industrial applications. Existing 5G-enabled systems suffer from latencies exceeding 10ms, which are inadequate for applications requiring sub-millisecond response times, such as autonomous industrial control and predictive maintenance. This research aims to develop and validate a 6G-enabled Digital Twin framework that achieves ultra-low latency communication and real-time synchronization between physical industrial assets and their digital counterparts, specifically targeting bearing fault detection as a critical industrial use case. The proposed framework integrates terahertz communications (0.1-1 THz), intelligent reflecting surfaces, and edge artificial intelligence within a five-layer architecture. Experimental validation was conducted using the Case Western Reserve University (CWRU) bearing dataset, implementing comprehensive feature extraction (15 time and frequency domain features) and Random Forest classification algorithms. The system performance was evaluated against traditional WiFi-6 and 5G networks across multiple metrics, including classification accuracy, end-to-end latency, and scalability. It achieved 97.7% fault classification accuracy with 0.8ms end-to-end latency, representing a 15.6x improvement over WiFi-6 (12.5ms) and 5.25x improvement over 5G (4.2ms) networks. The system demonstrated superior scalability with sub-linear processing time growth and maintained consistent performance across four bearing fault categories (normal, inner race, outer race, and ball faults) with macro-averaged F1-scores exceeding 97%.

Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from a large model running remotely to a small model running on-device. However, this incurs a communication delay that breaks real-time requirements and does not guarantee that both models will operate on the same data at the same time. We propose knowledge boosting, a novel technique that allows a large model to operate on time-delayed input during inference, while still boosting small model performance. Using a streaming neural network that processes 8 ms chunks, we evaluate different speech separation and enhancement tasks with communication delays of up to six chunks or 48 ms. Our results show larger gains where the performance gap between the small and large models is wide, demonstrating a promising method for large-small model collaboration for low-latency applications. Code, dataset, and audio samples available at https://knowledgeboosting.cs.washington.edu/.

Remote inference allows lightweight devices to leverage powerful cloud models. However, communication network latency makes predictions stale and unsuitable for real-time tasks. To address this, we introduce Dedelayed, a delay-corrective method that mitigates arbitrary remote inference delays, allowing the local device to produce low-latency outputs in real time. Our method employs a lightweight local model that processes the current frame and fuses in features that a heavyweight remote model computes from past frames. On video from the BDD100K driving dataset, Dedelayed improves semantic segmentation accuracy over the stronger of the local-only and remote-only baselines across all realistic communication network delays beyond 33 ms. Without incurring additional delay, it improves accuracy by 6.4 mIoU compared to fully local inference and 9.8 mIoU compared to remote inference, for a round-trip delay of 100 ms. The advantage grows under longer delays and higher-motion scenes, as delay-mitigated split inference sustains accuracy more effectively, providing clear advantages for real-time tasks that must remain aligned with the current world state.

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit payload crossing network and storage boundaries, making KV a dominant end-to-end bottleneck. Existing KV compression are typically static runtime configurations, despite production service context varies over time in workload mix, bandwidth, and SLO/quality budgets. As a result, a fixed choice can be suboptimal or even increase latency. We present KVServe, the first service-aware and adaptive KV communication compression framework for disaggregated LLM serving: KVServe (1) unifies KV compression into a modular strategy space with new components and cross-method recomposition; (2) introduces Bayesian Profiling Engine that efficiently searches this space and distills a 3D Pareto candidate set, reducing 50times offline search overhead; and (3) deploys a Service-Aware Online Controller that combines an analytical latency model with a lightweight bandit to select profiles under constraints and correct offline-to-online mismatch. Integrated into vLLM and evaluated across datasets, models, GPUs and networks, KVServe achieves up to 9.13times JCT speedup in PD-separated serving and up to 32.8times TTFT reduction in KV-disaggregated serving.

We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adapt offline models through chunking or sliding windows, Voxtral Realtime is trained end-to-end for streaming, with explicit alignment between audio and text streams. Our architecture builds on the Delayed Streams Modeling framework, introducing a new causal audio encoder and Ada RMS-Norm for improved delay conditioning. We scale pretraining to a large-scale dataset spanning 13 languages. At a delay of 480ms, Voxtral Realtime achieves performance on par with Whisper, the most widely deployed offline transcription system. We release the model weights under the Apache 2.0 license.

Edge deployment of large language models (LLMs) increasingly relies on libraries of lightweight LoRA adapters, yet GPU/DRAM can keep only a small resident subset at a time. Serving a request through a non-resident adapter requires paging its weights from storage, incurring measurable latency. This creates a two-timescale online control problem: on a slow timescale, the system selects which adapters remain resident in fast memory, while on a fast timescale it routes each request to an adapter whose context-dependent utility is unknown a priori. The two decisions are tightly coupled: the cache determines the cost of exploration, and the router determines which adapters receive informative feedback. We formulate this joint caching-and-routing problem as a two-timescale contextual bandit and propose POLAR (Paging and Online Learning for Adapter Routing). POLAR pairs a cache-aware LinUCB router with an epoch-based cache controller. We study two variants. A fixed-epoch version provides a robust baseline with worst-case regret guarantees under arbitrary contexts. An epoch-doubling version, POLAR+, adds forced exploration and improved cache optimization to achieve mathcal{O}(dNT+KT) sublinear regret under stochastic regularity and cacheability conditions, where N is the adapter count, K the cache size, d the context dimension, and T the horizon. The routing term matches the standard contextual-bandit rate up to logarithmic factors, showing that the memory hierarchy does not fundamentally slow routing learning. Experiments using 15 real LoRA adapters for Qwen2.5-7B together with measured GPU paging latencies show that adaptive cache control substantially outperforms non-adaptive baselines and exhibits scaling trends consistent with the theory.

Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase information, creating a significant streaming bottleneck. Furthermore, regression-based acoustic modeling frequently induces spectral over-smoothing artifacts. To address these limitations, this paper proposes a novel end-to-end non-autoregressive architecture optimized for ultra-low latency block-wise generation, directly modeling the highly compressed discrete latent space of the Mimi neural audio codec. Integrating a modified FastSpeech 2 backbone with a progressive depth-wise sequential decoding strategy, the architecture dynamically conditions 32 layers of residual vector quantization codes. This mechanism resolves phonetic alignment degradation and manages the complexity of high-fidelity discrete representations without temporal autoregressive overhead. Experimental evaluations on English and Malay datasets validate its language-independent deployment capability. Compared to conventional continuous regression models, the proposed architecture demonstrates quantitative improvements in fundamental voicing accuracy and mitigates high-frequency spectral degradation. It achieves ultra-low latency inference, translating to a 10.6-fold absolute acceleration over conventional cascaded pipelines. Crucially, the system achieves an average time-to-first-byte latency of 48.99 milliseconds, falling significantly below the human perception threshold for real-time interactive streaming. These results firmly establish the proposed architecture as a highly optimized solution for deploying real-time streaming speech interfaces.

GPU collective communication is typically optimized for bandwidth, yet many emerging workloads are increasingly limited by latency. Long-context decode-heavy large language model (LLM) inference is a prime example, where serving large models requires multiple GPUs, and many small collectives lie directly on the critical path of token generation. Therefore, even microsecond of overhead can impact performance and cost. In this work, we study how to approach the hardware Speed-of-Light (SoL) lower bound for GPU collectives within a scale-up network. We identify key principles for near-optimal designs, including barrier-free synchronization and efficient use of symmetric memory and multicast. Building on NCCL's device-side API, we develop low-latency interfaces for constructing custom collective kernels and use them to implement new symmetric collectives in NCCL. Microbenchmarks show substantial latency reductions for small and medium messages, reducing overhead to within 7% of the absolute SoL lower bound. When integrated into real applications, these kernels improve inter-token latency and throughput in LLM inference and accelerate cuSOLVERMp, demonstrating benefits for both AI inference and traditional HPC workloads.

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms of resource and latency requirements, as a result of the diverse applications and the dynamic execution nature of LLMs. Existing systems are fundamentally limited in handling these characteristics and cause problems such as severe queuing delays, poor tail latencies, and SLO violations. We introduce Llumnix, an LLM serving system that reacts to such heterogeneous and unpredictable requests by runtime rescheduling across multiple model instances. Similar to context switching across CPU cores in modern operating systems, Llumnix reschedules requests to improve load balancing and isolation, mitigate resource fragmentation, and differentiate request priorities and SLOs. Llumnix implements the rescheduling with an efficient and scalable live migration mechanism for requests and their in-memory states, and exploits it in a dynamic scheduling policy that unifies the multiple rescheduling scenarios elegantly. Our evaluations show that Llumnix improves tail latencies by an order of magnitude, accelerates high-priority requests by up to 1.5x, and delivers up to 36% cost savings while achieving similar tail latencies, compared against state-of-the-art LLM serving systems. Llumnix is publicly available at https://github.com/AlibabaPAI/llumnix.

Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end model that performs simultaneous speech-to-text translation and streaming transcription by encoding READ/WRITE decisions into a probabilistic WAIT token mechanism. We also introduce Decoder Time Dilation, a mechanism that reduces autoregressive overhead and ensures a balanced training distribution. Additionally, we present a supervised fine-tuning strategy that trains the model to recover from delays, significantly improving the quality-latency trade-off. Evaluated on English-to-Japanese, German, and Russian, Hikari achieves new state-of-the-art BLEU scores in both low- and high-latency regimes, outperforming recent baselines.

Generating realistic, dyadic talking head video requires ultra-low latency. Existing chunk-based methods require full non-causal context windows, introducing significant delays. This high latency critically prevents the immediate, non-verbal feedback required for a realistic listener. To address this, we present DyStream, a flow matching-based autoregressive model that could generate video in real-time from both speaker and listener audio. Our method contains two key designs: (1) we adopt a stream-friendly autoregressive framework with flow-matching heads for probabilistic modeling, and (2) We propose a causal encoder enhanced by a lookahead module to incorporate short future context (e.g., 60 ms) to improve quality while maintaining low latency. Our analysis shows this simple-and-effective method significantly surpass alternative causal strategies, including distillation and generative encoder. Extensive experiments show that DyStream could generate video within 34 ms per frame, guaranteeing the entire system latency remains under 100 ms. Besides, it achieves state-of-the-art lip-sync quality, with offline and online LipSync Confidence scores of 8.13 and 7.61 on HDTF, respectively. The model, weights and codes are available.

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the LLM in parallel. Small models that utilise activations from the LLM currently achieve the fastest decoding speeds. However, we identify several limitations of SD models including the lack of on-policyness during training and partial observability. To address these shortcomings, we propose a more grounded architecture for small models by introducing a Mixture of Attentions for SD. Our novel architecture can be applied in two scenarios: a conventional single device deployment and a novel client-server deployment where the small model is hosted on a consumer device and the LLM on a server. In a single-device scenario, we demonstrate state-of-the-art speedups improving EAGLE-2 by 9.5% and its acceptance length by 25%. In a client-server setting, our experiments demonstrate: 1) state-of-the-art latencies with minimal calls to the server for different network conditions, and 2) in the event of a complete disconnection, our approach can maintain higher accuracy compared to other SD methods and demonstrates advantages over API calls to LLMs, which would otherwise be unable to continue the generation process.

Spiking Neural Networks (SNNs) are energy efficient alternatives to commonly used deep neural networks (DNNs). Through event-driven information processing, SNNs can reduce the expensive compute requirements of DNNs considerably, while achieving comparable performance. However, high inference latency is a significant hindrance to the edge deployment of deep SNNs. Computation over multiple timesteps not only increases latency as well as overall energy budget due to higher number of operations, but also incurs memory access overhead of fetching membrane potentials, both of which lessen the energy benefits of SNNs. To overcome this bottleneck and leverage the full potential of SNNs, we propose an Iterative Initialization and Retraining method for SNNs (IIR-SNN) to perform single shot inference in the temporal axis. The method starts with an SNN trained with T timesteps (T>1). Then at each stage of latency reduction, the network trained at previous stage with higher timestep is utilized as initialization for subsequent training with lower timestep. This acts as a compression method, as the network is gradually shrunk in the temporal domain. In this paper, we use direct input encoding and choose T=5, since as per literature, it is the minimum required latency to achieve satisfactory performance on ImageNet. The proposed scheme allows us to obtain SNNs with up to unit latency, requiring a single forward pass during inference. We achieve top-1 accuracy of 93.05%, 70.15% and 67.71% on CIFAR-10, CIFAR-100 and ImageNet, respectively using VGG16, with just 1 timestep. In addition, IIR-SNNs perform inference with 5-2500X reduced latency compared to other state-of-the-art SNNs, maintaining comparable or even better accuracy. Furthermore, in comparison with standard DNNs, the proposed IIR-SNNs provide25-33X higher energy efficiency, while being comparable to them in classification performance.

As scalable inference services become popular, the cold start latency of an inference engine becomes important. Today, vLLM has evolved into the de facto inference engine of choice for many inference workloads. Although popular, due to its complexity and rapid evolution, there has not been a systematic study of its startup latency. With major architectural innovations such as the V1 API and the introduction of torch.compile, this paper presents the first detailed performance characterization of vLLM startup latency. We break down the startup process into six foundational steps and demonstrate that it is predominantly CPU bound. Each step exhibits consistent and interpretable scaling trends with respect to model-level and system-level parameters, enabling fine-grained attribution of latency sources. Building on these insights, we develop a lightweight analytical model that accurately predicts vLLM startup latency for a given hardware configuration, providing actionable guidance for resource planning in large-scale inference environments. All benchmarking datasets, analysis tools, and prediction scripts are open sourced at https://github.com/upb-cn/vllm-startup-profiler.

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with identical model replicas. This design overlooks the potential of heterogeneous deployments, where models of different sizes and capabilities enable finer trade-offs between latency and performance. However, heterogeneity introduces new challenges in scheduling across models with diverse throughput and performance. We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters that jointly improves end-to-end latency and task performance. Chimera applies semantic routing to estimate per-model confidence scores for each request, predicts the total remaining output length of the workflow, and estimates per-model congestion using in-flight predicted token volumes for load balancing. We evaluate Chimera on representative agentic workflows for code generation and math reasoning using multiple heterogeneous LLM configurations. Across comparable settings, Chimera traces the best latency-performance frontier, reducing end-to-end latency by 1.2--2.4times and improving task performance by 8.0-9.5 percentage points on average over competitive baselines including vLLM.

We propose an open-source framework for Command-style dictation that addresses the gap between resource-intensive Online systems and high-latency Batch processing. Our approach uses Voice Activity Detection (VAD) to segment audio and transcribes these segments in parallel using Whisper models, enabling efficient multiplexing across audios. Unlike proprietary systems like SuperWhisper, this framework is also compatible with most ASR architectures, including widely used CTC-based models. Our multiplexing technique maximizes compute utilization in real-world settings, as demonstrated by its deployment in around 15% of India's courtrooms. Evaluations on live data show consistent latency reduction as user concurrency increases, compared to sequential batch processing. The live demonstration will showcase our open-sourced implementation and allow attendees to interact with it in real-time.

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level optimizations, lacking a holistic serving framework that addresses the unique memory dynamics of diffusion processes in production. We identify a critical "memory footprint crisis" specific to dLLMs, driven by monolithic logit tensors and the severe resource oscillation between compute-bound "Refresh" phases and bandwidth-bound "Reuse" phases. To bridge this gap, we present dLLM-Serve, an efficient dLLM serving system that co-optimizes memory footprint, computational scheduling, and generation quality. dLLM-Serve introduces Logit-Aware Activation Budgeting to decompose transient tensor peaks, a Phase-Multiplexed Scheduler to interleave heterogeneous request phases, and Head-Centric Sparse Attention to decouple logical sparsity from physical storage. We evaluate dLLM-Serve on diverse workloads (LiveBench, Burst, OSC) and GPUs (RTX 4090, L40S). Relative to the state-of-the-art baseline, dLLM-Serve improves throughput by 1.61times-1.81times on the consumer-grade RTX 4090 and 1.60times-1.74times on the server-grade NVIDIA L40S, while reducing tail latency by nearly 4times under heavy contention. dLLM-Serve establishes the first blueprint for scalable dLLM inference, converting theoretical algorithmic sparsity into tangible wall-clock acceleration across heterogeneous hardware.

The complexity of large language model (LLM) serving workloads has substantially increased due to the integration with external tool invocations, such as ChatGPT plugins. In this paper, we identify a new opportunity for efficient LLM serving for requests that trigger tools: tool partial execution alongside LLM decoding. To this end, we design Conveyor, an efficient LLM serving system optimized for handling requests involving external tools. We introduce a novel interface for tool developers to expose partial execution opportunities to the LLM serving system and a request scheduler that facilitates partial tool execution. Our results demonstrate that tool partial execution can improve request completion latency by up to 38.8%.

Voice dictation is an increasingly important text input modality. Existing systems that allow both dictation and editing-by-voice restrict their command language to flat templates invoked by trigger words. In this work, we study the feasibility of allowing users to interrupt their dictation with spoken editing commands in open-ended natural language. We introduce a new task and dataset, TERTiUS, to experiment with such systems. To support this flexibility in real-time, a system must incrementally segment and classify spans of speech as either dictation or command, and interpret the spans that are commands. We experiment with using large pre-trained language models to predict the edited text, or alternatively, to predict a small text-editing program. Experiments show a natural trade-off between model accuracy and latency: a smaller model achieves 30% end-state accuracy with 1.3 seconds of latency, while a larger model achieves 55% end-state accuracy with 7 seconds of latency.

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing approaches including Early and Late Penalties and Constrained Alignments penalize emission delay by manipulating per-token or per-frame probability prediction in sequence transducer models. While being successful in reducing delay, these approaches suffer from significant accuracy regression and also require additional word alignment information from an existing model. In this work, we propose a sequence-level emission regularization method, named FastEmit, that applies latency regularization directly on per-sequence probability in training transducer models, and does not require any alignment. We demonstrate that FastEmit is more suitable to the sequence-level optimization of transducer models for streaming ASR by applying it on various end-to-end streaming ASR networks including RNN-Transducer, Transformer-Transducer, ConvNet-Transducer and Conformer-Transducer. We achieve 150-300 ms latency reduction with significantly better accuracy over previous techniques on a Voice Search test set. FastEmit also improves streaming ASR accuracy from 4.4%/8.9% to 3.1%/7.5% WER, meanwhile reduces 90th percentile latency from 210 ms to only 30 ms on LibriSpeech.

Long-form automatic speech recognition (ASR) requires both high accuracy and low latency, but existing systems force a trade-off between the two. Chunk-based pipelines process audio in parallel windows for low latency, but lose cross-chunk context and need brittle heuristics to align speakers and timestamps at boundaries. Long-context ASR models resolve everything in a single pass for better accuracy, but are an order of magnitude slower. We propose Murmur, an inference system that overcomes this trade-off by operating at two levels. At the inter-chunk level, we revisit the chunk-based pipeline for modern long-context ASR, treating chunk size as a tunable hyperparameter, and show that intermediate chunk sizes strike a good balance of accuracy and latency. At the intra-chunk level, we exploit attention sparsity through a sliding window KV cache eviction policy applied to both output and speech tokens. On AMI-IHM, Murmur matches single-pass accuracy while reducing latency by 4.2x, with further gains from token eviction at less than 1% relative tcpWER degradation. The code of Murmur is available at https://github.com/uw-syfi/Murmur.

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past signal, while non-causal models are exposed to a window of future frames at each step to increase predictive accuracy. This dichotomy amounts to a trade-off for real-time Automatic Speech Recognition (ASR) system design: profit from the low-latency benefit of strictly-causal architectures while accepting predictive performance limitations, or realize the modeling benefits of future-context models accompanied by their higher latency penalty. In this work, we relax the constraints of this choice and present the Adaptive Non-Causal Attention Transducer (ANCAT). Our architecture is non-causal in the traditional sense, but executes in a low-latency, streaming manner by dynamically choosing when to rely on future context and to what degree within the audio stream. The resulting mechanism, when coupled with our novel regularization algorithms, delivers comparable accuracy to non-causal configurations while improving significantly upon latency, closing the gap with their causal counterparts. We showcase our design experimentally by reporting comparative ASR task results with measures of accuracy and latency on both publicly accessible and production-scale, voice-assistant datasets.

Large Mixture-of-Experts (MoE) model inference is challenging due to high resource demands and dynamic workloads. Existing solutions often deploy the entire model as a single monolithic unit, which applies a unified resource configuration to both attention and expert modules despite their different requirements, leading to limited scalability and resource inefficiency. In this paper, we propose Janus, a scalable MoE inference system that disaggregates attention and experts on separate GPU sub-clusters, enabling each module to be managed and scaled independently. Janus incorporates three key designs for efficient, disaggregated MoE inference. First, it proposes an adaptive two-phase communication scheme that exploits intra- and inter-node bandwidth hierarchies for low-latency data exchange. Second, motivated by the memory-bound nature of MoE modules, Janus introduces a lightweight scheduler and implements it as a GPU kernel to balance the number of activated experts across GPUs at minimal overhead, thereby reducing inference latency. Third, Janus performs fine-grained resource management to dynamically adjust expert placement and independently scale attention and MoE resources to improve overall efficiency. Evaluation shows Janus achieves up to 3.9 higher perGPU throughput than state-of-the-art systems while meeting per-token latency requirements.

Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal throughput for inference serving. However, due to the unpredictability of LLM execution, the first-come-first-serve (FCFS) scheduling policy employed by current LLM serving systems suffers from head-of-line (HoL) blocking issues and long job response times. In this paper, we propose a new efficient LLM inference serving framework, named ALISE. The key design paradigm of ALISE is to leverage a novel speculative scheduler by estimating the execution time for each job and exploiting such prior knowledge to assign appropriate job priority orders, thus minimizing potential queuing delays for heterogeneous workloads. Furthermore, to mitigate the memory overhead of the intermediate key-value (KV) cache, we employ a priority-based adaptive memory management protocol and quantization-based compression techniques. Evaluations demonstrate that in comparison to the state-of-the-art solution vLLM, ALISE improves the throughput of inference serving by up to 1.8x and 2.1x under the same latency constraint on the Alpaca and ShareGPT datasets, respectively.

In this work, we present a new approach for fast tracking on multiwire proportional chambers with neural networks. The tracking networks are developed and adapted for the first-level trigger at hadron collider experiments. We use Monte Carlo samples generated by Geant4 with a custom muon chamber, which resembles part of the thin gap chambers from the ATLAS experiment, for training and performance evaluations. The chamber has a total of seven gas gaps, where the first and last gas gaps are displaced by ~1.5 m. Each gas gap has 50 channels with a size of 18-20 mm. Two neural network models are developed and presented: a convolutional neural network and a neural network optimized for the detector configuration of this study. In the latter network, a convolution layer is provided for each of three groups formed from 2-3 gas gaps of the chamber, and the outputs are fed into multilayer perceptrons in sequence. Both networks are transformed into hardware description language and implemented in Virtex UltraScale+ FPGA. The angular resolution is 2 mrad, which is comparable to the maximum resolution of the detector estimated by the minimum chi2 method. The latency achieved by the implemented firmware is less than 100 ns, and the throughput rate is 160 MHz.

AI Video Assistant emerges as a new paradigm for Real-time Communication (RTC), where one peer is a Multimodal Large Language Model (MLLM) deployed in the cloud. This makes interaction between humans and AI more intuitive, akin to chatting with a real person. However, a fundamental mismatch exists between current RTC frameworks and AI Video Assistants, stemming from the drastic shift in Quality of Experience (QoE) and more challenging networks. Measurements on our production prototype also confirm that current RTC fails, causing latency spikes and accuracy drops. To address these challenges, we propose Artic, an AI-oriented RTC framework for MLLM Video Assistants, exploring the shift from "humans watching video" to "AI understanding video." Specifically, Artic proposes: (1) Response Capability-aware Adaptive Bitrate, which utilizes MLLM accuracy saturation to proactively cap bitrate, reserving bandwidth headroom to absorb future fluctuations for latency reduction; (2) Zero-overhead Context-aware Streaming, which allocates limited bitrate to regions most important for the response, maintaining accuracy even under ultra-low bitrates; and (3) Degraded Video Understanding Benchmark, the first benchmark evaluating how RTC-induced video degradation affects MLLM accuracy. Prototype experiments using real-world uplink traces show that compared with existing methods, Artic significantly improves accuracy by 15.12% and reduces latency by 135.31 ms. We will release the benchmark and codes at https://github.com/pku-netvideo/DeViBench.

Efficient scheduling of LLM inference tasks is essential for achieving low latency and high throughput, particularly with the growing use of reasoning-capable LLMs. Traditional strategies like First-Come-First-Serve (FCFS) often suffer from Head-of-Line (HOL) blocking, where long-running tasks delay shorter ones queued behind them. In this paper, we introduce PARS, a prompt-aware LLM task scheduler that improves serving efficiency by approximating shortest-job-first (SJF) scheduling through pairwise ranking with margin ranking loss. PARS focuses on impactful scheduling decisions and is seamlessly integrated into the state-of-the-art LLM serving system vLLM. It effectively predicts response-length-based task ordering, reducing latency with minimal overhead. Extensive experiments across multiple LLMs and real-world inference datasets show that PARS significantly improves performance, including for reasoning workloads. Furthermore, our cross-model evaluations demonstrate that the design generalizes well, enabling effective scheduling even when predictors are trained on different LLMs.

Music generation models can produce high-fidelity coherent accompaniment given complete audio input, but are limited to editing and loop-based workflows. We study real-time audio-to-audio accompaniment: as a model hears an input audio stream (e.g., a singer singing), it has to also simultaneously generate in real-time a coherent accompanying stream (e.g., a guitar accompaniment). In this work, we propose a model design considering inevitable system delays in practical deployment with two design variables: future visibility t_f, the offset between the output playback time and the latest input time used for conditioning, and output chunk duration k, the number of frames emitted per call. We train Transformer decoders across a grid of (t_f,k) and show two consistent trade-offs: increasing effective t_f improves coherence by reducing the recency gap, but requires faster inference to stay within the latency budget; increasing k improves throughput but results in degraded accompaniment due to a reduced update rate. Finally, we observe that naive maximum-likelihood streaming training is insufficient for coherent accompaniment where future context is not available, motivating advanced anticipatory and agentic objectives for live jamming.

Serial LLM inference backends -- such as Ollama -- process requests one at a time under FCFS admission, causing Head-of-Line Blocking (HOLB) under mixed workloads at high utilisation: short factual queries can be delayed by minutes behind long generation jobs. While cloud-scale deployments mitigate HOLB via continuous batching (vLLM, Orca), these solutions require tens of GB of VRAM for concurrent KV-caches -- infeasible for memory-constrained edge and local deployments that rely on serial request dispatch. We present \clairvoyant, a drop-in sidecar proxy for any serial OpenAI-compatible backend (e.g., Ollama, llama.cpp). \clairvoyant predicts response length from 19 lightweight lexical features via an ONNX-exported XGBoost classifier, achieving 0.029\,ms per-request latency (four orders of magnitude below typical generation time). Because admission scheduling depends on relative ordering rather than exact prediction, the system optimises ranking fidelity, achieving 62--96\% in-distribution and 52--66\% cross-distribution accuracy across natural conversation datasets. We find that curated instruction datasets are degenerate training sources for length prediction: GPT-imposed brevity constraints reduce Long-class representation to under 0.02\% of examples, making natural conversation logs the only viable training source. End-to-end GPU benchmarks on an RTX~4090 show 70--76\% P50 latency reduction for short requests under maximum queue pressure (100 concurrent requests) and 17\% under steady-state Poisson arrivals (ρ=0.74). \clairvoyant is open-source and requires no modifications to the inference backend.

Diffusion-based video super-resolution (VSR) methods achieve strong perceptual quality but remain impractical for latency-sensitive settings due to reliance on future frames and expensive multi-step denoising. We propose Stream-DiffVSR, a causally conditioned diffusion framework for efficient online VSR. Operating strictly on past frames, it combines a four-step distilled denoiser for fast inference, an Auto-regressive Temporal Guidance (ARTG) module that injects motion-aligned cues during latent denoising, and a lightweight temporal-aware decoder with a Temporal Processor Module (TPM) that enhances detail and temporal coherence. Stream-DiffVSR processes 720p frames in 0.328 seconds on an RTX4090 GPU and significantly outperforms prior diffusion-based methods. Compared with the online SOTA TMP, it boosts perceptual quality (LPIPS +0.095) while reducing latency by over 130x. Stream-DiffVSR achieves the lowest latency reported for diffusion-based VSR, reducing initial delay from over 4600 seconds to 0.328 seconds, thereby making it the first diffusion VSR method suitable for low-latency online deployment. Project page: https://jamichss.github.io/stream-diffvsr-project-page/

Heterogeneous LLM serving stacks split scheduling into two layers that optimize in isolation: model routers pick a model from quality and cost signals while ignoring instance load, and serving load balancers optimize queues while ignoring quality. We present RouteBalance, a serving-aware scheduling layer that fuses both into a single online assignment over concrete model instances, jointly trading off quality, latency, and cost. A batched in-process predictor stack and dead-reckoned instance state keep the joint decision cheap on the request hot path (approx32 ms at 12 req/s). On a 13-instance, 28-GPU heterogeneous cluster serving four model sizes, a single deployed RouteBalance stack traces the upper region of the three-way quality-cost-throughput frontier. Sweeping one weight vector reaches both the highest routing-decision quality (DeepEval 0.419, +0.013 over the strongest baseline, 95% CI [{+}0.005,{+}0.022]; the ordering holds when a second judge re-scores the actually served text) and, at its cost-priority corner, per-request cost that ties the cheapest baseline. With router engineering equalized against concurrent-scoring baseline variants we build, its balanced preset serves at 2.8 s and 30 req/s, leading 2.6 to 4.1times ahead of enhanced BEST-Route at high load. (Deploying those routers as published, one serial scoring call per request, makes them collapse 23times under load, a deployment-architecture effect we isolate separately, not the routing result.) A four-arm isolation shows the benefit follows from pricing latency at model-selection time; the learned predictors contribute calibration and SLO headroom rather than the headline frontier. Code: https://github.com/AKafakA/route-balance

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However, the model still tends to delay the predictions towards the end and thus has much higher partial latency compared to a conventional ASR model. To address this issue, we look at encouraging the E2E model to emit words early, through an algorithm called FastEmit [3]. Naturally, improving on latency results in a quality degradation. To address this, we explore replacing the LSTM layers in the encoder of our E2E model with Conformer layers [4], which has shown good improvements for ASR. Secondly, we also explore running a 2nd-pass beam search to improve quality. In order to ensure the 2nd-pass completes quickly, we explore non-causal Conformer layers that feed into the same 1st-pass RNN-T decoder, an algorithm called Cascaded Encoders [5]. Overall, we find that the Conformer RNN-T with Cascaded Encoders offers a better quality and latency tradeoff for streaming ASR.

Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache. We study the opposite regime: low-latency, small-batch, on-device physical-AI serving, where interactive LLM agents, speech systems, and robot policies repeatedly branch, reset, interrupt, and re-enter under tight responsiveness budgets. We introduce execution-state capsules, a graph-bound checkpoint and restore mechanism for the complete restorable state at a committed boundary. FlashRT is a white-box, backend-facing kernel runtime whose evaluated NVIDIA CUDA backend runs captured graph plans over contiguous static buffers with no block-table indirection. Because the live state is a closed set of named buffers, a capsule can snapshot, restore, fork, or roll back the whole execution boundary, including KV, recurrent state, convolution state, MTP state, and metadata. This moves reuse from token-addressed KV fragments to graph-bound execution-state boundaries. On an RTX 5090, capsule restore is byte-exact at the stored-state level and token-identical under greedy decode. A KV-only ablation diverges, showing that recurrent state is load-bearing. GPU-resident snapshot and restore are sub-millisecond, and TTFT speedup over cold prefill grows from 3.9x at 2k tokens to 27x at 16k tokens. On Jetson AGX Thor and DGX Spark, the same correctness and structural properties hold. Capsules are not a replacement for high-throughput KV-cache serving; they define a complementary latency-first serving point for explicit execution-state reuse.

We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises the interactive output stream from 192x336 to 640x368 while preserving approximately 200 ms model-side signal-to-signal latency at 25 FPS. The higher-resolution stream supports scene-grounded mid-shot agents whose posture, gaze, hands, nearby objects, and local scene layout remain legible during real-time conversation. To support the larger visual stream without adding user-visible delay, v0.2 keeps the thinker as a single-GPU low-latency path for streaming perception, the short language/state Transformer pass that builds the generation cache, and final decoding. The performer becomes a multi-GPU Ulysses-style context-parallel group for the expensive next-unit latent generation. Each performer rank writes incoming K/V into a pre-sharded local cache. The long high-resolution latent video sequence is split across ranks for denoising and gathered through Ulysses communication, while the much shorter audio latent sequence is generated without sequence sharding. In this split, the thinker's language/state computation reaches the performer only as K/V conditioning, so no separate language sequence has to be communicated inside the performer group. This concentrates additional hardware on visual generation while preserving the compact thinker-performer boundary, keeping total remote interaction latency at approximately 550 ms when a 350 ms bidirectional network budget is included.

While low-latency interaction is critical for spoken dialogue, cascaded architectures are often bottlenecked by reactive turn-completion detection. We propose Endpoint Anticipation, shifting from reactive detection to proactive forecasting of end-of-turn signals. Our speech-based model anticipates endpoints upto 2.56 seconds in advance, enabling speculative execution of LLM and TTS pipelines on partial context. We introduce metrics to quantify the trade-off between realized latency reduction and computational redundancy. Evaluation across conversational and task-oriented datasets shows our model consistently outperforms competitive VAP-based baselines. Integration with the Unmute framework demonstrates a 505 ms average latency reduction with a 28.4% increase in speculative computation, effectively masking sequential bottlenecks to enable complex reasoning in real-time speech-to-speech interaction.

Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is hindered by the significant resource requirements during inference. In this paper, we study two approaches for mitigating these challenges: employing a cache to store previous queries and learning a model multiplexer to choose from an ensemble of models for query processing. Theoretically, we provide an optimal algorithm for jointly optimizing both approaches to reduce the inference cost in both offline and online tabular settings. By combining a caching algorithm, namely Greedy Dual Size with Frequency (GDSF) or Least Expected Cost (LEC), with a model multiplexer, we achieve optimal rates in both offline and online settings. Empirically, simulations show that the combination of our caching and model multiplexing algorithms greatly improves over the baselines, with up to 50times improvement over the baseline when the ratio between the maximum cost and minimum cost is 100. Experiments on real datasets show a 4.3times improvement in FLOPs over the baseline when the ratio for FLOPs is 10, and a 1.8times improvement in latency when the ratio for average latency is 1.85.

Although existing 3D perception algorithms have demonstrated significant improvements in performance, their deployment on edge devices continues to encounter critical challenges due to substantial runtime latency. We propose a new benchmark tailored for online evaluation by considering runtime latency. Based on the benchmark, we build a Latency-Aware 3D Streaming Perception (LASP) framework that addresses the latency issue through two primary components: 1) latency-aware history integration, which extends query propagation into a continuous process, ensuring the integration of historical feature regardless of varying latency; 2) latency-aware predictive detection, a module that compensates the detection results with the predicted trajectory and the posterior accessed latency. By incorporating the latency-aware mechanism, our method shows generalization across various latency levels, achieving an online performance that closely aligns with 80\% of its offline evaluation on the Jetson AGX Orin without any acceleration techniques.

Simultaneous speech translation (SimulST) systems aim at generating their output with the lowest possible latency, which is normally computed in terms of Average Lagging (AL). In this paper we highlight that, despite its widespread adoption, AL provides underestimated scores for systems that generate longer predictions compared to the corresponding references. We also show that this problem has practical relevance, as recent SimulST systems have indeed a tendency to over-generate. As a solution, we propose LAAL (Length-Adaptive Average Lagging), a modified version of the metric that takes into account the over-generation phenomenon and allows for unbiased evaluation of both under-/over-generating systems.

Auto-regressive Large Language Models (LLMs) demonstrate remarkable performance across different domains such as vision and language processing. However, due to sequential processing through a stack of transformer layers, autoregressive decoding faces significant computation/latency challenges, particularly in resource-constrained environments like mobile and edge devices. Existing approaches in literature that aim to improve latency via skipping layers have two distinct flavors - 1) Early exit, and 2) Input-agnostic heuristics where tokens exit at pre-determined layers irrespective of input sequence. Both the above strategies have limitations - the former cannot be applied to handle KV Caching necessary for speed-ups in modern framework and the latter does not capture the variation in layer importance across tasks or more generally, across input sequences. To address both limitations, we propose FiRST, an algorithm that reduces inference latency by using layer-specific routers to select a subset of transformer layers adaptively for each input sequence - the prompt (during the prefill stage) decides which layers will be skipped during decoding. FiRST preserves compatibility with KV caching enabling faster inference while being quality-aware. FiRST is model-agnostic and can be easily enabled on any pre-trained LLM. Our approach reveals that input adaptivity is critical - indeed, different task-specific middle layers play a crucial role in evolving hidden representations depending on tasks. Extensive experiments show that FiRST significantly reduces latency while outperforming other layer selection strategies in quality metics. It retains competitive performance to base model (without layer skipping) and in some cases, even improves upon it. FiRST is thus a promising and efficient solution for LLM deployment in low-resource environments.

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop that adaptively allocates requests across heterogeneous accelerators based on real-time cost and capacity signals. The approach sustains low latency and high throughput by dynamically shifting between cost-optimized and capacity-optimized modes, ensuring the most efficient use of expensive compute resources under fluctuating availability. Evaluated using the Stable Diffusion model, the framework consistently meets latency targets, automatically redirects traffic during capacity shortfalls, and capitalizes on lower-cost accelerators when possible. These results highlight how a feedback-driven deployment strategy, spanning the entire software and hardware stack, can help organizations efficiently scale generative AI workloads while maintaining resilience in the face of limited accelerator capacity.

AI Video Chat emerges as a new paradigm for Real-time Communication (RTC), where one peer is not a human, but a Multimodal Large Language Model (MLLM). This makes interaction between humans and AI more intuitive, as if chatting face-to-face with a real person. However, this poses significant challenges to latency, because the MLLM inference takes up most of the response time, leaving very little time for video streaming. Due to network uncertainty and instability, transmission latency becomes a critical bottleneck preventing AI from being like a real person. To address this, we propose Artic, an AI-oriented Real-time Communication framework, exploring the network requirement shift from "humans watching video" to "AI understanding video". To reduce bitrate dramatically while maintaining MLLM accuracy, we propose Context-Aware Video Streaming that recognizes the importance of each video region for chat and allocates bitrate almost exclusively to chat-important regions. To avoid packet retransmission, we propose Loss-Resilient Adaptive Frame Rate that leverages previous frames to substitute for lost/delayed frames while avoiding bitrate waste. To evaluate the impact of video streaming quality on MLLM accuracy, we build the first benchmark, named Degraded Video Understanding Benchmark (DeViBench). Finally, we discuss some open questions and ongoing solutions for AI Video Chat.

LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling policies that fail to adapt to heterogeneous workload characteristics. We observe that prompt-length variations lead to distinct performance bottlenecks, motivating an adaptive scheduling strategy. LAPS disaggregates multi-turn long-prefill requests from short-prefill ones and introduces a length-aware smart batching mechanism for short-prefill workloads. It adopts a dual-queue design that supports temporal disaggregation on a single prefill instance or spatial disaggregation across multiple instances. For short-prefill batches, a batch waiting window and CUDA Graph-based clustering mitigate interference from heterogeneous computation, reducing batching delay and lowering average latency. In real multi-turn workloads, LAPS reduces prefill latency by over 30\% compared to vanilla SGLang under prefill-decode disaggregation, and further decreases SLO violations by 28\% in multi-instance deployments with vanilla data-parallel configuration. Compared to the SGLang router with load balancing, it further lowers SLO violations by 12\% in multi-GPU settings. Under high concurrency and mixed-request scenarios, LAPS improves request throughput by 35\% serving Qwen2.5-32B model for prefill instance, demonstrating its effectiveness in optimizing heterogeneous LLM serving workloads.

As more devices connect to the internet, it becomes crucial to address their limitations and basic security needs. While much research focuses on utilizing ML and DL to tackle security challenges, there is often a tendency to overlook the practicality and feasibility of implementing these methods in real-time settings. This oversight stems from the constrained processing power and memory of certain devices (IoT devices), as well as concerns about the generalizability of these approaches. Focusing on the detection of DNS-tunneling attacks in a router as a case study, we present an end-to-end process designed to effectively address these challenges. The process spans from developing a lightweight DNS-tunneling detection model to integrating it into a resource-constrained device for real-time detection. Through our experiments, we demonstrate that utilizing stateless features for training the ML model, along with features chosen to be independent of the network configuration, leads to highly accurate results. The deployment of this carefully crafted model, optimized for embedded devices across diverse environments, resulted in high DNS-tunneling attack detection with minimal latency. With this work, we aim to encourage solutions that strike a balance between theoretical advancements and the practical applicability of ML approaches in the ever-evolving landscape of device security.

Human-Robot Collaboration (HRC) in shared physical spaces using Augmented Reality (AR) interfaces is powered by Simultaneous Localization and Mapping (SLAM). Existing multi-agent SLAM systems rely on an edge server to combine visual findings of multiple resource-constrained agents, perform computation, and schedule updates to their local maps. However, the edge treats all agents uniformly and ignores the fundamentally different latency requirements of heterogeneous HRC agents: robots and head-mounted AR users. This uniform resource allocation often results in high lag for user manipulation, as it does not meet the stringent latency requirements of AR. In this work, we design, implement, and evaluate SHARE, a user-centric SLAM system that strategically prioritizes AR user experience while maintaining accurate tracking performance for robots. SHARE builds a first-of-its-kind experience model for HRC agents and adaptively adjusts transmission priorities to match it. To reduce end-to-end latency, SHARE leverages the redundancy of visual features acquired by agents in shared human-robot workspaces to reduce computation time induced by edge-based processing. Real-world deployment with commercial AR headsets and a ground robot achieves 13.22 ms average latency for AR users (43.3% reduction from baseline) while maintaining sub-2-centimeter tracking accuracy. User studies further reveal statistically significant improvements in user perception.

Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response requires the prior generation of a written response, and (2) speech sequences are significantly longer than text sequences. This study addresses these issues by extending the input and output sequences of the language model to support the parallel generation of text and speech. Our experiments on spoken question answering tasks demonstrate that our approach improves latency while maintaining the quality of response content. Additionally, we show that latency can be further reduced by generating speech in multiple sequences. Demo samples are available at https://rinnakk.github.io/research/publications/PSLM.

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming Transformer-Transducer that jointly generates automatic speech recognition (ASR) and speech translation (ST) outputs using a single decoder. To produce ASR and ST content effectively with minimal latency, we propose a joint token-level serialized output training method that interleaves source and target words by leveraging an off-the-shelf textual aligner. Experiments in monolingual (it-en) and multilingual (\{de,es,it\}-en) settings demonstrate that our approach achieves the best quality-latency balance. With an average ASR latency of 1s and ST latency of 1.3s, our model shows no degradation or even improves output quality compared to separate ASR and ST models, yielding an average improvement of 1.1 WER and 0.4 BLEU in the multilingual case.

Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary strong-vs-weak decisions and couple learned parameters to specific model identities, requiring retraining whenever the catalog changes. We present HyDRA (Hybrid Dynamic Routing Architecture), a framework that predicts fine-grained, multi-dimensional capability requirements per query and matches them against configuration-defined model profiles via shortfall matching. A ModernBERT encoder with K=4 independent sigmoid heads scores each query along reasoning, code generation, debugging, and tool use; a shortfall-matching algorithm then selects the cheapest model whose capabilities meet the predicted requirements. The deployed predictor runs at 86 ms median CPU inference latency in production, and is fully decoupled from the model catalog -- adding or removing models requires only a configuration change, with zero retraining. On SWE-Bench Verified (5-model pool: GPT-5.4-mini, Claude Haiku 4.5, GPT-5.3 Codex, Claude Sonnet 4.6, GPT-5.4), HyDRA's tunable shortfall threshold spans three regimes: peak-quality exceeds the always-strong Claude Sonnet 4.6 baseline (75.4% vs. 74.2% resolution) at 12.9% cost savings; iso-quality matches Sonnet at 54.1% cost savings, a 6x improvement over our prior in-house binary router at 9.1%; aggressive pushes savings to 72.5% for a 3.2-point quality trade. Results generalize across LiveCodeBench, BigCodeBench, and tau-bench. HyDRA is deployed to all users in GitHub Copilot's VS Code Chat auto-mode and -- to our knowledge for the first time in the LLM routing literature -- demonstrates language-invariant routing across CJK, European, and other script families.

Edge intelligence paradigm is increasingly demanded by the emerging autonomous systems, such as robotics. Beyond ensuring privacy-preserving operation and resilience in connectivity-limited environments, edge deployment offers significant energy and cost advantages over cloud-based solutions. However, deploying large language models (LLMs) for reasoning tasks on edge GPUs faces critical challenges from strict latency constraints and limited computational resources. To navigate these constraints, developers must balance multiple design factors - choosing reasoning versus non-reasoning architectures, selecting appropriate model sizes, allocating token budgets, and applying test-time scaling strategies - to meet target latency and optimize accuracy. Yet guidance on optimal combinations of these variables remains scarce. In this work, we present EdgeReasoning, a comprehensive study characterizing the deployment of reasoning LLMs on edge GPUs. We systematically quantify latency-accuracy tradeoffs across various LLM architectures and model sizes. We systematically evaluate prompt-based and model-tuning-based techniques for reducing reasoning token length while maintaining performance quality. We further profile test-time scaling methods with varying degrees of parallelism to maximize accuracy under strict latency budgets. Through these analyses, EdgeReasoning maps the Pareto frontier of achievable accuracy-latency configurations, offering systematic guidance for optimal edge deployment of reasoning LLMs.

Streaming speech enhancement requires balancing algorithmic latency against quality, yet existing approaches largely treat this as a binary causal versus non-causal choice. LaCo-SENet addresses this issue with two mechanisms parameterized by a single training-time hyperparameter. First, asymmetric temporal padding redistributes past and future context in convolutions, enabling systematic latency configuration. Second, dual-buffer streaming combines state buffers for past context with lookahead buffers that supply future context at both the input and feature levels. Selective state updates also prevent future-frame leakage into the streaming state, ensuring training-inference consistency. On VoiceBank+DEMAND, a fixed-budget (1.37M parameters) backbone yields a family of models spanning 12.5-75.0 ms, with PESQ rising from 3.35 to 3.43. At just 12.5 ms (fully causal), a PESQ of 3.35 matches or exceeds the prior causal state-of-the-art (3.27 at 46.5 ms).

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent Neural Network Transducer (RNN-T) model and a second-pass Listen, Attend, Spell (LAS) rescorer that surpasses a conventional model in both quality and latency. On the quality side, we incorporate a large number of utterances across varied domains to increase acoustic diversity and the vocabulary seen by the model. We also train with accented English speech to make the model more robust to different pronunciations. In addition, given the increased amount of training data, we explore a varied learning rate schedule. On the latency front, we explore using the end-of-sentence decision emitted by the RNN-T model to close the microphone, and also introduce various optimizations to improve the speed of LAS rescoring. Overall, we find that RNN-T+LAS offers a better WER and latency tradeoff compared to a conventional model. For example, for the same latency, RNN-T+LAS obtains a 8% relative improvement in WER, while being more than 400-times smaller in model size.

Recent advances in spoken dialogue systems have brought increased attention to human-like full-duplex voice interactions. However, our comprehensive review of this field reveals several challenges, including the difficulty in obtaining training data, catastrophic forgetting, and limited scalability. In this work, we propose SoulX-Duplug, a plug-and-play streaming state prediction module for full-duplex spoken dialogue systems. By jointly performing streaming ASR, SoulX-Duplug explicitly leverages textual information to identify user intent, effectively serving as a semantic VAD. To promote fair evaluation, we introduce SoulX-Duplug-Eval, extending widely used benchmarks with improved bilingual coverage. Experimental results show that SoulX-Duplug enables low-latency streaming dialogue state control, and the system built upon it outperforms existing full-duplex models in overall turn management and latency performance. We have open-sourced SoulX-Duplug and SoulX-Duplug-Eval.

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional generation-length-based definition breaks down: tool latency decouples inference time from generation length. We propose Timely Machine, redefining test-time as wall-clock time, where models dynamically adjust strategies based on time budgets. We introduce Timely-Eval, a benchmark spanning high-frequency tool calls, low-frequency tool calls, and time-constrained reasoning. By varying tool latency, we find smaller models excel with fast feedback through more interactions, while larger models dominate high-latency settings via superior interaction quality. Moreover, existing models fail to adapt reasoning to time budgets. We propose Timely-RL to address this gap. After cold-start supervised fine-tuning, we use reinforcement learning to enhance temporal planning. Timely-RL improves time budget awareness and consistently boosts performance across Timely-Eval. We hope our work offers a new perspective on test-time scaling for the agentic era.

X-Codec-2.0 has shown strong performance in neural audio compression and multilingual speech modeling, operating at a 50 Hz latent rate and a 16 kHz sampling rate using frozen HuBERT features. While effective, this configuration limits temporal efficiency and audio fidelity. In this work, we explore a simple and effective modification by introducing additional pooling and increasing the decoder hop size. This reduces the latent rate from 50 Hz to 25 Hz and simultaneously raises the output sampling rate from 16 kHz to 24 kHz, improving efficiency and perceptual quality without altering the core architecture. Evaluated on the multilingual Common Voice 17 test set, the proposed configuration achieves a 0.29 MOS improvement over the original X-Codec-2.0 baseline based on UTMOSv2, and attains the best reported performance among all codecs operating at 25 Hz. The source code, checkpoints, and generation comparisons are released at https://huggingface.co/Scicom-intl/xcodec2-25TPS-24k{https://huggingface.co/Scicom-intl/xcodec2-25TPS-24k}.

To schedule LLM inference, the shortest job first (SJF) principle is favorable by prioritizing requests with short output lengths to avoid head-of-line (HOL) blocking. Existing methods usually predict a single output length for each request to facilitate scheduling. We argue that such a point estimate does not match the stochastic decoding process of LLM inference, where output length is uncertain by nature and determined by when the end-of-sequence (EOS) token is sampled. Hence, the output length of each request should be fitted with a distribution rather than a single value. With an in-depth analysis of empirical data and the stochastic decoding process, we observe that output length follows a heavy-tailed distribution and can be fitted with the log-t distribution. On this basis, we propose a simple metric called Tail Inflated Expectation (TIE) to replace the output length in SJF scheduling, which adjusts the expectation of a log-t distribution with its tail probabilities to account for the risk that a request generates long outputs. To evaluate our TIE scheduler, we compare it with three strong baselines, and the results show that TIE reduces the per-token latency by 2.31times for online inference and improves throughput by 1.42times for offline data generation.

Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of speakers. We adopt the time-domain speech separation method and the recently proposed Graph-PIT to build a super low-latency online speech separation model, which is very important for the real application. The low-latency time-domain encoder with a small stride leads to an extremely long feature sequence. We proposed a simple yet efficient model named Skipping Memory (SkiM) for the long sequence modeling. Experimental results show that SkiM achieves on par or even better separation performance than DPRNN. Meanwhile, the computational cost of SkiM is reduced by 75% compared to DPRNN. The strong long sequence modeling capability and low computational cost make SkiM a suitable model for online CSS applications. Our fastest real-time model gets 17.1 dB signal-to-distortion (SDR) improvement with less than 1-millisecond latency in the simulated meeting-style evaluation.

Efficiently serving neural network models with low latency is becoming more challenging due to increasing model complexity and parameter count. Model quantization offers a solution which simultaneously reduces memory footprint and compute requirements. However, aggressive quantization may lead to an unacceptable loss in model accuracy owing to differences in sensitivity to numerical imperfection across different layers in the model. To address this challenge, we propose a mixed-precision post training quantization (PTQ) approach that assigns different numerical precisions to tensors in a network based on their specific needs, for a reduced memory footprint and improved latency while preserving model accuracy. Previous works rely on layer-wise Hessian information to determine numerical precision, but as we demonstrate, Hessian estimation is typically insufficient in determining an effective ordering of layer sensitivities. We address this by augmenting the estimated Hessian with additional information to capture inter-layer dependencies. We demonstrate that this consistently improves PTQ performance along the accuracy-latency Pareto frontier across multiple models. Our method combines second-order information and inter-layer dependencies to guide a bisection search, finding quantization configurations within a user-configurable model accuracy degradation range. We evaluate the effectiveness of our method on the ResNet50, MobileNetV2, and BERT models. Our experiments demonstrate latency reductions compared to a 16-bit baseline of 25.48%, 21.69%, and 33.28% respectively, while maintaining model accuracy to within 99.99% of the baseline model.

Efficient parallelism is necessary for achieving low-latency, high-throughput inference with large language models (LLMs). Tensor parallelism (TP) is the state-of-the-art method for reducing LLM response latency, however GPU communications reduces combined token throughput. On the other hand, data parallelism (DP) obtains a higher throughput yet is slow in response latency. Best of both worlds does not exist, and it is not possible to combine TP and DP because of the KV cache variance across the parallelisms. We notice Sequence Parallelism (SP - Ulysses in training) has similar properties as DP but with KV cache invariance. We adapt SP to inference, and combine it with TP to get the best of both worlds. Our solution: Shift Parallelism. Shift Parallelism dynamically switches across TP and SP, and minimizes latency in low traffic without losing throughput in high traffic. The efficient GPU communications of Shift Parallelism yields up to i) 1.51x faster response in interactive workloads and ii) 50% higher throughput in batch workloads, compared to a TP-only solution. We evaluate Shift Parallelism with real-world production traces with dynamic traffic patterns as well as synthetic benchmarking patterns across models, context sizes, and arrival rates. All results affirm the same: Shift Parallelism has a better the latency vs. throughput tradeoff than TP or DP, and hence obtains low latency without degrading throughput in dynamic workloads.

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the compute-intensive prefill phase, where long-running requests monopolize resources and delay higher-priority ones, leading to widespread time-to-first-token (TTFT) SLO violations. While chunked prefill enables interruptibility, it introduces an inherent trade-off between responsiveness and throughput: reducing chunk size improves response latency but degrades computational efficiency, whereas increasing chunk size maximizes throughput but exacerbates blocking. This necessitates an adaptive preemption mechanism. However, dynamically balancing execution granularity against scheduling overheads remains a key challenge. In this paper, we propose FlowPrefill, a TTFT-goodput-optimized serving system that resolves this conflict by decoupling preemption granularity from scheduling frequency. To achieve adaptive prefill scheduling, FlowPrefill introduces two key innovations: 1) Operator-Level Preemption, which leverages operator boundaries to enable fine-grained execution interruption without the efficiency loss associated with fixed small chunking; and 2) Event-Driven Scheduling, which triggers scheduling decisions only upon request arrival or completion events, thereby supporting efficient preemption responsiveness while minimizing control-plane overhead. Evaluation on real-world production traces shows that FlowPrefill improves maximum goodput by up to 5.6times compared to state-of-the-art systems while satisfying heterogeneous SLOs.

Modern key-value storage engines built on Log-Structured Merge-trees (LSM-trees), such as RocksDB and LevelDB, rely heavily on the performance of their compaction operations, which are impacted by a complex set of interdependent configuration parameters. Manually tuning these parameters for optimal performance demands considerable expertise, while traditional auto-tuning approaches struggle with the enormous search space and low sample efficiency inherent to this domain. In recent years, Large Language Models (LLMs) have demonstrated strong capabilities in code generation and logical reasoning, offering new possibilities for system optimization. However, applying LLMs to real-time compaction tuning in such latency-sensitive environments is a double-edged sword. While large-scale LLMs can offer superior reasoning for strategy generation, their high inference latency and computational cost make them impractical for interactive, low-latency tuning. In contrast, small-scale LLMs achieve low latency but often at the expense of reasoning accuracy and tuning effectiveness. In this paper, we first evaluate this trade-off by analyzing the compaction-tuning performance and inference latency of LLMs at different scales in an LSM-tree-based tuning case. We then characterize the performance of LSM-tree on RocksDB v8.8.1, with a focus on adjusting the key compaction-related parameters under db_bench workloads. Our experimental results show a clear positive correlation between model capability and tuning effectiveness.

Channel state information (CSI) is essential for adaptive beamforming and maintaining robust links in wireless communication systems. However, acquiring CSI incurs significant overhead, consuming up to 25% of spectrum resources in 5G networks due to frequent pilot transmissions at millisecond-scale intervals. Recent approaches aim to reduce this burden by reconstructing CSI from spatiotemporal RF measurements, such as signal strength and direction-of-arrival. While effective in offline settings, these methods often suffer from inference latencies in the 5-100 ms range, making them impractical for real-time systems. We present GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels, a method that achieves accurate channel reconstruction with latency in the low-millisecond regime or below. GSpaRC represents the RF environment using a compact set of 3D Gaussian primitives, each parameterized by a lightweight neural model augmented with physics-informed features such as distance-based attenuation. Unlike traditional vision-based splatting pipelines, GSpaRC is tailored for RF reception: it employs an equirectangular projection onto a hemispherical surface centered at the receiver to reflect omnidirectional antenna behavior. A custom CUDA pipeline enables fully parallelized directional sorting, splatting, and rendering across frequency and spatial dimensions. Evaluated on multiple RF datasets, GSpaRC achieves similar CSI reconstruction fidelity to recent state-of-the-art methods while reducing training and inference time by over an order of magnitude. These results illustrate that modest GPU computation can substantially reduce pilot overhead, making GSpaRC a scalable low-latency approach for channel estimation in 5G and future wireless systems.

Web proxies such as NGINX commonly rely on least-recently-used (LRU) eviction, which is size agnostic and can thrash under periodic bursts and mixed object sizes. We introduce Cold-RL, a learned eviction policy for NGINX that replaces LRU's forced-expire path with a dueling Deep Q-Network served by an ONNX sidecar within a strict microsecond budget. On each eviction, Cold-RL samples the K least-recently-used objects, extracts six lightweight features (age, size, hit count, inter-arrival time, remaining TTL, and last origin RTT), and requests a bitmask of victims; a hard timeout of 500 microseconds triggers immediate fallback to native LRU. Policies are trained offline by replaying NGINX access logs through a cache simulator with a simple reward: a retained object earns one point if it is hit again before TTL expiry. We compare against LRU, LFU, size-based, adaptive LRU, and a hybrid baseline on two adversarial workloads. With a 25 MB cache, Cold-RL raises hit ratio from 0.1436 to 0.3538, a 146 percent improvement over the best classical baseline; at 100 MB, from 0.7530 to 0.8675, a 15 percent gain; and at 400 MB it matches classical methods (about 0.918). Inference adds less than 2 percent CPU overhead and keeps 95th percentile eviction latency within budget. To our knowledge, this is the first reinforcement learning eviction policy integrated into NGINX with strict SLOs.

Higher Degree by Research (HDR) candidates increasingly depend on cloud-provisioned virtual machines and local GPU hardware for their computational experiments, yet a persistent and under-addressed gap exists between having compute resources and using them productively. Cloud and infrastructure teams can provision virtual machines, but the path from a raw VM to a reproducible, GPU-ready research environment remains a significant barrier for researchers who are domain experts, not systems engineers. We identify this gap as a missing adapter layer between cloud provisioning and interactive research work. We present a lightweight, open-source solution built on k3s and Coder that implements this adapter layer and is already in active use in our research workspace environment. Our CI/CD pipeline connects GitHub directly to the local cluster, deploying research projects in under five minutes. We define a concrete metrics framework for evaluating this layer -- covering deployment latency, environment reproducibility, onboarding friction, and resource utilisation -- and establish baselines against which improvements can be measured.

Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is impractical for fluent voice conversations. We propose LLM2Speech, an architecture to synthesize speech while text is being generated by an LLM which yields significant latency reduction. LLM2Speech mimics the predictions of a non-streaming teacher model while limiting the exposure to future context in order to enable streaming. It exploits the hidden embeddings of the LLM, a by-product of the text generation that contains informative semantic context. Experimental results show that LLM2Speech maintains the teacher's quality while reducing the latency to enable natural conversations.

Emerging Large Language Model (LLM) system patterns, such as disaggregated inference, Mixture-of-Experts (MoE) routing, and asynchronous reinforcement fine-tuning, require flexible point-to-point communication beyond simple collectives. Existing implementations are locked to specific Network Interface Controllers (NICs), hindering integration into inference engines and portability across hardware providers. We present TransferEngine, which bridges the functionality of common NICs to expose a uniform interface. TransferEngine exposes one-sided WriteImm operations with a ImmCounter primitive for completion notification, without ordering assumptions of network transport, transparently managing multiple NICs per GPU. We demonstrate peak throughput of 400 Gbps on both NVIDIA ConnectX-7 and AWS Elastic Fabric Adapter (EFA). We showcase TransferEngine through three production systems: (1) KvCache transfer for disaggregated inference with dynamic scaling, (2) RL weight updates achieving 1.3 seconds for trillion-parameter models, and (3) MoE dispatch/combine implementation exceeding DeepEP decode latency on ConnectX-7, with the first viable latencies on EFA. We demonstrate that our portable point-to-point communication complements collectives while avoiding lock-in.

Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource-constrained on-device settings, selecting an appropriate large language model (LLM) backbone is a critical challenge: models must balance accuracy with strict inference latency and hardware efficiency constraints. This makes hardware-software co-design a game-changing requirement for on-device LLM deployment, where each hardware platform demands a tailored architectural solution. We propose a hardware co-design law that jointly captures model accuracy and inference performance. Specifically, we model training loss as an explicit function of architectural hyperparameters and characterise inference latency via roofline modelling. We empirically evaluate 1,942 candidate architectures on NVIDIA Jetson Orin, training 170 selected models for 10B tokens each to fit a scaling law relating architecture to training loss. By coupling this scaling law with latency modelling, we establish a direct accuracy-latency correspondence and identify the Pareto frontier for hardware co-designed LLMs. We further formulate architecture search as a joint optimisation over precision and performance, deriving feasible design regions under industrial hardware and application budgets. Our approach reduces architecture selection from months to days. At the same latency as Qwen2.5-0.5B on the target hardware, our co-designed architecture achieves 19.42% lower perplexity on WikiText-2. To our knowledge, this is the first principled and operational framework for hardware co-design scaling laws in on-device LLM deployment. We will make the code and related checkpoints publicly available.

Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural architecture search (NAS) which can be computationally expensive. We address this problem by providing an end-to-end technique that optimizes for model's Floating Point Operations (FLOPs) or for on-device latency via a novel ell_1{ell_2} latency surrogate. Our algorithm is versatile and can be used with many popular compression methods including pruning, low-rank factorization, and quantization. Crucially, it is fast and runs in almost the same amount of time as single model training; which is a significant training speed-up over standard NAS methods. For BERT compression on GLUE fine-tuning tasks, we achieve 50% reduction in FLOPs with only 1% drop in performance. For compressing MobileNetV3 on ImageNet-1K, we achieve 15% reduction in FLOPs, and 11% reduction in on-device latency without drop in accuracy, while still requiring 3times less training compute than SOTA compression techniques. Finally, for transfer learning on smaller datasets, our technique identifies 1.2times-1.4times cheaper architectures than standard MobileNetV3, EfficientNet suite of architectures at almost the same training cost and accuracy.

Automated speech recognition (ASR) models have gained prominence for applications such as captioning, speech translation, and live transcription. This paper studies Whisper and two model variants: one optimized for live speech streaming and another for offline transcription. Notably, these models have been found to generate hallucinated content, reducing transcription reliability. Furthermore, larger model variants exhibit increased latency and pose challenges for deployment on resource-constrained devices. This study analyzes the similarities and differences between three Whisper models, qualitatively examining their distinct capabilities. Next, this study quantifies the impact of model quantization on latency and evaluates its viability for edge deployment. Using the open source LibriSpeech dataset, this paper evaluates the word error rate (WER) along with latency analysis of whispercpp using 3 quantization methods (INT4, INT5, INT8). Results show that quantization reduces latency by 19\% and model size by 45\%, while preserving transcription accuracy. These findings provide insights into the optimal use cases of different Whisper models and edge device deployment possibilities. All code, datasets, and implementation details are available in a public GitHub repository: https://github.com/allisonandreyev/WhisperQuantization.git

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve general LLM but fail with Low-Rank Adaptation (LoRA) inference due to three key limitations: 1) massive parameter redundancy among functions where 99% of weights are unnecessarily duplicated, 2) costly artifact loading latency beyond LLM loading, and 3) magnified resource contention when serving multiple LoRA LLMs. These inefficiencies lead to massive GPU wastage, increased Time-To-First-Token (TTFT), and high monetary costs. We propose ServerlessLoRA, a novel serverless inference system designed for faster and cheaper LoRA LLM serving. ServerlessLoRA enables secure backbone LLM sharing across isolated LoRA functions to reduce redundancy. We design a pre-loading method that pre-loads comprehensive LoRA artifacts to minimize cold-start latency. Furthermore, ServerlessLoRA employs contention aware batching and offloading to mitigate GPU resource conflicts during bursty workloads. Experiment on industrial workloads demonstrates that ServerlessLoRA reduces TTFT by up to 86% and cuts monetary costs by up to 89% compared to state-of-the-art LLM inference solutions.

We present LatentCSI, a novel method for generating images of the physical environment from WiFi CSI measurements that leverages a pretrained latent diffusion model (LDM). Unlike prior approaches that rely on complex and computationally intensive techniques such as GANs, our method employs a lightweight neural network to map CSI amplitudes directly into the latent space of an LDM. We then apply the LDM's denoising diffusion model to the latent representation with text-based guidance before decoding using the LDM's pretrained decoder to obtain a high-resolution image. This design bypasses the challenges of pixel-space image generation and avoids the explicit image encoding stage typically required in conventional image-to-image pipelines, enabling efficient and high-quality image synthesis. We validate our approach on two datasets: a wide-band CSI dataset we collected with off-the-shelf WiFi devices and cameras; and a subset of the publicly available MM-Fi dataset. The results demonstrate that LatentCSI outperforms baselines of comparable complexity trained directly on ground-truth images in both computational efficiency and perceptual quality, while additionally providing practical advantages through its unique capacity for text-guided controllability.