new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Nov 6

Submitted by

taesiri

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

nvidia

Submitted by

zhangkangning

Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training

SJUT1

Shanghai JiaoTong University

Submitted by

linggm

Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand

CarnegieMellonU

Carnegie Mellon University

Submitted by

Wenxuan123

SLA: Scaling Spatial-Language-Action Model via Continual Pre-training

Submitted by

taesiri

WeLM-Image: A Unified Image Generation Model towards Visual Intelligence

·
16 authors

Submitted by

Lyricccco

TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

MMLab-CUHK

Submitted by

eric-xiang

EvoMemState: Evolving Memory State for Personal Agents

·
10 authors

Submitted by

zx-Wu

VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents

antgroup

Submitted by

NischayDnk

Towards Foundation Decision Models: Drex

nace-ai

Submitted by

ucasmjc

Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models

DAGroup-PKU

Submitted by

zen-E

On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer

KingsCollegeLondon

King's College London

Submitted by

kwanY

EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure

Submitted by

harryjo97

Future Representation Distillation for Imagination-free World Action Models

kaist-ai

Submitted by

kimspacehuni

HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation

Seoul National University

Submitted by

wuxiaojun

Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling

IDEA-FinAI

Submitted by

scofield7419

From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence

Oxford

University of Oxford

1

Submitted by

zly-idleness

Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models

CUHKSZ

Chinese University of Hong Kong, Shenzhen

Submitted by

tushaar

Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout

google

Submitted by

yifusuyi

SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization

ByteDance-Seed

Submitted by

QuillerJ12

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

brownu

Brown University

Submitted by

marcusinthesky

Information Games: Strategic Crowding and Firm Repositioning in Language-Model Space

uct

University of Cape Town

Submitted by

hongst

Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens

nlpai-lab

NLP & AI - Korea University

Submitted by

ryhara

Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation

·
6 authors

Submitted by

pengkaiScience

NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma

InfiX-ai

Submitted by

FlippyDora

OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery

·
3 authors

Submitted by

gurayozgur

Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition

FraunhoferIGD

2

Submitted by

shredder67

SynthFaces: Balanced Large Scale Human Dataset

·
4 authors

1

Submitted by

mingchaocc

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

stable-ai

1

Submitted by

harrychangtw

Identically Trained Language Models Break on Different Jailbreaks

cerulean-works