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

Feb 3

Submitted by

2pd

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

SberRoboticsCenter

Sber Robotics Center

Submitted by

taesiri

Kimi K2.5: Visual Agentic Intelligence

moonshotai

Submitted by

YuZeng260

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

·
15 authors

Submitted by

YuZeng260

Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

·
16 authors

1

Submitted by

Luo2003

Closing the Loop: Universal Repository Representation with RPG-Encoder

·
13 authors

Submitted by

taesiri

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

·
11 authors

Submitted by

Ayanami0730

WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora

muset-ai

Submitted by

IgnoraZ

FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

muset-ai

1

Submitted by

chenmouxiang

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Qwen

Qwen

1

Submitted by

Ayanami0730

Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles

muset-ai

Submitted by

zehongma

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

PekingUniversity

Peking University

Submitted by

mrapplexz

SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference Optimization

fpsigma

Floating Point Sigma Lab

Submitted by

Lingaaaaaaa

RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System

princeton-ai

Princeton AI Lab

Submitted by

lmquan

PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

microsoft

Submitted by

SereinH

Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation

·
9 authors

Submitted by

zhuhz22

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

thu-ml

Tsinghua Machine Learning Group

Submitted by

taesiri

FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space

ByteDance

Submitted by

Dvir

Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention

·
6 authors

Submitted by

SivanSX

Toward Cognitive Supersensing in Multimodal Large Language Model

Submitted by

almogtavor

Rethinking Selective Knowledge Distillation

tau

Tel Aviv University

Submitted by

shizhuo2

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

huanyu112

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

·
12 authors

Submitted by

comin

Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

·
14 authors

2

Submitted by

YUXU915

Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning

tencent

1

Submitted by

JialiangZhu

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

microsoft

Submitted by

Ningyu

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

alibabagroup

Submitted by

Beckham808

Show, Don't Tell: Morphing Latent Reasoning into Image Generation

Submitted by

jshin49

Generative Visual Code Mobile World Models

trillionlabs

Submitted by

Xueqing

Ebisu: Benchmarking Large Language Models in Japanese Finance

TheFinAI

1

Submitted by

AngLv

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning

ByteDance-Seed

Submitted by

Harold328

LoopViT: Scaling Visual ARC with Looped Transformers

·
6 authors

1

Submitted by

pakoromilas

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding

·
5 authors

Submitted by

huxueyu

AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios

·
45 authors

Submitted by

AndongChen

Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling

·
6 authors

Submitted by

OceanSky

TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios

meituan

1

Submitted by

happzy2633

CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation

m-a-p

Multimodal Art Projection

Submitted by

lliutianc

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training

Submitted by

wangfuyun

PromptRL: Prompt Matters in RL for Flow-Based Image Generation

CUHK

Submitted by

Xkev

Sparse Reward Subsystem in Large Language Models

Stanford

Submitted by

TimothyCzp

Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning

RUC-AIBOX

Submitted by

hankaixyz

An Empirical Study of World Model Quantization

huawei-noah

HUAWEI Noah's Ark Lab

Submitted by

BryanW

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

·
11 authors

Submitted by

cherubicxn

Interacted Planes Reveal 3D Line Mapping

AntResearch

Submitted by

hp-l33

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

Submitted by

JonnyYu828

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration

Zhejiang University

1

Submitted by

ReRaWo

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

·
11 authors

Submitted by

thinkwee

Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models

KCL

King's College London

Submitted by

safal312

On the Limits of Layer Pruning for Generative Reasoning in LLMs

newyorkuniversity

New York University

Submitted by

Lost-Cloud

Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning

LiAuto-Foundation-Model

LiAuto Foundation Model

Submitted by

hp-l33

Mano: Restriking Manifold Optimization for LLM Training

2

Submitted by

rockerritesh

On the Relationship Between Representation Geometry and Generalization in Deep Neural Networks

·
1 authors

3

Submitted by

Peter2023HuggingFace

Implicit neural representation of textures

·
3 authors

Submitted by

isaacchung

Cross-Lingual Stability of LLM Judges Under Controlled Generation: Evidence from Finno-Ugric Languages

·
2 authors

Submitted by

yunqu

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models

·
11 authors

1

Submitted by

emirhanbilgic

AI-Generated Image Detectors Overrely on Global Artifacts: Evidence from Inpainting Exchange

·
3 authors

1

Submitted by

nennomp

ParalESN: Enabling parallel information processing in Reservoir Computing

·
4 authors

1

Submitted by

menik1126

OVD: On-policy Verbal Distillation

·
10 authors

Submitted by

meetdoshi90

Influence Guided Sampling for Domain Adaptation of Text Retrievers

·
4 authors

Submitted by

MYMY-young

Enhancing Multi-Image Understanding through Delimiter Token Scaling

·
6 authors

Submitted by

Eavn

Internal Flow Signatures for Self-Checking and Refinement in LLMs

BiasLab2025

Submitted by

yunhuijang

INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery

·
4 authors

Submitted by

mrpeerat

SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia

aisingapore

Submitted by

Junhyuk129

Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory

·
5 authors