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 3

Submitted by

DrewJin0827

Wave Forcing: Towards Speed-of-Light Streaming Video Generation

SJTU-DENG-Lab

DENG Lab @ SJTU

Submitted by

dongguanting

CoworkOS:Scaling Agent Coworkers for Real-world Automation

RUC

Renmin University of China

Submitted by

visity

Advances in Agentic Computer Graphics

UTEXAS

University of Texas at Austin

Submitted by

neversa

Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement

VideoRebirthAI

Submitted by

yxl66666

CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements

·
18 authors

Submitted by

yuxinzuo

Democratizing Robot-Use Agents: A Unified Harness with Open Models

·
28 authors

Submitted by

vyokky

NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale

beipo-ai

Submitted by

bangpro

Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay

kaist-ai

Submitted by

zzzhu

Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning

·
15 authors

2

Submitted by

NeilLeeNTU

PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments

·
4 authors

Submitted by

zmli

SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training

antgroup

Submitted by

Geralt-Targaryen

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

codefuse-ai

Submitted by

Silin-Chen

CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents

·
7 authors

1

Submitted by

SookX

When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?

·
3 authors

Submitted by

wuuuuuz

Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents

SJTU

Shanghai Jiao Tong University

1

Submitted by

kenchan0226

Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning

·
5 authors

Submitted by

SpiridonSunRotator

FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell

yresearch

Yandex Research

Submitted by

yudian

DecisionRank: On-Policy Distillation for Decision-Model Rerankers

meta

Submitted by

Dingy-Kang

DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers

·
2 authors

Submitted by

Ruurd

BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion

UMCUtrecht

University Medical Center Utrecht

Submitted by

luyh20

WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining

·
12 authors

Submitted by

SeanWu25

Measuring AI Agents as Teammates with Collaborative Intelligence

StanfordUniversity

Stanford University

Submitted by

SXQiu

MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads

PekingUniversity

Peking University

Submitted by

talzoomanzoo

Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer

GeorgiaTech

Georgia Institute of Technology

1

Submitted by

Debargha

LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

Case Western Reserve University

Submitted by

kehong

TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents

·
11 authors

Submitted by

shufanshen

On-Policy Self-Distillation with Teacher Evolution

UCAS

1

Submitted by

67L11

Cross-Primitive Consistency in Jev

·
4 authors

Submitted by

lixinyizju

TaoMate-FVSR:Audio-Guided Facial Video Restoration

Submitted by

HaoyuZhao

Can Large Language Model Agents Learn by Watching Tutorial Videos?

UniversityCollegeLondon

University College London

1

Submitted by

Garygedegege

Lab2Sim: Turning Real-World Experiment Videos into Interactive Virtual Experiments

PolyUHK

The Hong Kong Polytechnic University

Submitted by

smcleish

Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime

·
6 authors

Submitted by

Xalphinions

ProVe: Proposer-Verifier Decoding

·
6 authors

Submitted by

HughieHu

DR Pixel: Page-Native Deep Research with Vision-Language Models

Berkeley-NLP

Submitted by

67L11

Multi-Agent Relay Thinking

·
5 authors

Submitted by

leduckhai

Where Do Vision Language Models Fail at 3D Reasoning?

StanfordUniversity

Stanford University

Submitted by

monurcan

SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time

dtudk

Technical University of Denmark

Submitted by

gurayozgur

When Morphs Look Better: Face Image Quality as a Training-Free Signal for Morphing Attack Detection

FraunhoferIGD

Submitted by

zhaoshangziqi

Can Coding Agents Sustain Continual Evolution without Forgetting?

·
3 authors