<span class="bg-gradient-to-r from-amber-600 to-orange-500 bg-clip-text text-transparent">Paper Everyday

FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation

Vladislav Bargatin +3 more

Mi-Ripple: Restoring Images Degraded by Iterative AI Editing

Jiayin Chen +2 more

Computer Vision and Pattern RecognitionArtificial Intelligence

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Soohyun Ryu +2 more

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Haiwen Diao +64 more

arXivSep 6

TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation

Mingwei Li +2 more

Computer Vision and Pattern RecognitionMachine Learning

CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

Nhat-Tan Bui +9 more

arXivSep 6

Agentic Visual Generation: From Generative Models to Agentic Control

Yinming Huang +9 more

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Zhuoran Zhao +9 more

SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

Xingjian Ran +5 more

Computer Vision and Pattern RecognitionMachine Learning

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Igor Pavlovic +8 more

arXivSep 5

DriveZero: End-to-End Driving Beyond Human Demonstrations

Hao He +19 more

Computer Vision and Pattern RecognitionArtificial Intelligence

ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation

Javier del Pino +4 more

AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition

Shunpeng Chen +8 more

arXivAug 29

To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

Xiaobin Huang +5 more

Computer Vision and Pattern RecognitionComputation and Language

ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

Jitai Hao +3 more

WorldSculpt: Generating Compositional Worlds from Grounded Videos

Muyao Niu +11 more

TorchMorph: CUDA-accelerated Morphological Transforms

Kai Zhao

Computer Vision and Pattern RecognitionMachine Learning

MoTE: Mixture of Task Experts for Multi-Task Video Understanding

Muhammad Asad Ali +3 more

Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning

LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training

Andreas Hochlehnert +11 more

From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms

Jiangning Zhang +2 more

Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training

Wenxuan Shen +2 more

On-Policy Self-Distillation in Diffusion Models

Wei Zhou +16 more

Computer Vision and Pattern RecognitionComputation and LanguageInformation Retrieval

WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report

Junjie Zhou +5 more

arXivAug 20

Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs

Yunheng Li +6 more

arXivAug 21

EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment

Guray Ozgur +3 more

arXivAug 20

Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection

Guray Ozgur +2 more

Category

Artificial Intelligence(22 papers)

arXivAug 28

HyQuant: Hybrid-Precision Quantization for LLM Attention

Jiatong Ding +11 more

arXivSep 9

An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics

Ivan Moshkov +5 more

Artificial IntelligenceComputation and LanguageMultiagent Systems

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Yuxing Lu +3 more

Artificial IntelligenceComputation and LanguageComputer Vision and Pattern RecognitionMachine Learning

arXivSep 6

Reason Through the Latent! Making Latent Visual Reasoning Necessary

Suhyeong Park +2 more

Artificial IntelligenceMachine LearningOpticsQuantitative Methods

When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference

Ismail Erbas +2 more

τ^τ-Bench: An Environment for End-To-End, Realistic Agent Construction

Quan Shi +3 more

Artificial IntelligencePerformanceProgramming Languages

MaxKernel: Agentic Kernel Generation for TPUs

Shangkun Wang +9 more

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Yang Li +2 more

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

Mostafa Elhoushi +8 more

The Attention Triangle in Audio-Video Models

Sagi Polaczek +6 more

Iris: Climbing to the Search Frontier

Ziyuan Liu +8 more

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

Yihang Chen +5 more

Artificial IntelligenceDiscrete MathematicsMultiagent Systems

Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

Stephen Chung +2 more

CAFE: Self-Improving Search Agents Need Co-Evolving Feedback

Boyang Liu +17 more

Artificial IntelligenceMultiagent Systems

When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows

Yiheng Sun +5 more

Artificial IntelligenceComputation and LanguageMachine Learning

Automata from Agent Traces: Failure and Next-Step Prediction

Seonglae Cho +6 more

Artificial IntelligenceSoftware Engineering

AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace

Seonglae Cho, Donghyun Lee

Artificial IntelligenceComputation and LanguageSystems and Control

Meta^n: Recursive Self-Improvement through Emergent Depth

Zae Myung Kim +3 more

Artificial IntelligenceComputation and Language

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

Zhaochen Yu +7 more

Artificial IntelligenceComputation and LanguageMachine LearningMultiagent SystemsSoftware Engineering

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Sungho Park +12 more

ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts

YuanHang Xiao

Artificial IntelligenceComputer Vision and Pattern Recognition

From Generation to Simulation: How Far Are World Models from Being True Simulators?

Tong Wang +5 more

Category

Machine Learning(19 papers)

Beyond Solver Verdicts: Generative Reward Models for Autoformalization

Vikash Singh +7 more

Machine LearningArtificial IntelligenceComputation and Language

arXivSep 9

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Remco Hendriks

Machine LearningArtificial IntelligenceComputation and Language

Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks

Hongbang Yuan +2 more

Machine LearningArtificial Intelligence

Kalman Delta Networks: Uncertainty-aware Associative Memory

Ngoc Bui +2 more

Machine LearningDistributed, Parallel, and Cluster Computing

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Zili Wang +4 more

Miles v0.1: Production-Level Post-Training

RadixArk +12 more

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

Janghyeon Kim +3 more

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Youngrok Park +8 more

Machine LearningMachine Learning

Causal Foundation Models

Christopher Stith +2 more

Machine LearningArtificial IntelligenceComputation and Language

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

Zhiwei Zhang +8 more

Machine LearningArtificial IntelligenceComputation and Language

arXivAug 26

One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation

Justin Robert, Raheel Qader

Machine LearningArtificial Intelligence

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Zixun Huang +3 more

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Subham Sekhar Sahoo +16 more

Machine Learning

arXivAug 31

Group Adaptive Clipping Policy Optimization

Sheng Jia +3 more

Machine LearningArtificial Intelligence

On-policy Distillation with Verifiable Reward

Wenze Lin +7 more

Machine LearningArtificial IntelligenceComputation and Language

Best Practice Critic Optimization

Penghui Qi +2 more

Machine LearningInstrumentation and Methods for Astrophysics

What AstroPT knows about galaxies, and what that can teach us about LLMs

UniverseTBD +4 more

Machine LearningArtificial IntelligenceDistributed, Parallel, and Cluster ComputingEmerging TechnologiesQuantum Physics

arXivAug 14

Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning

Chun-Hua Lin +9 more

RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling

Ziyuan Wang +4 more

Machine LearningGenomics

Category

Robotics(11 papers)

Memory as Plans: World-Action Modeling with Memory-Grounded Planning

Sizhe Zhao +7 more

RoboticsArtificial Intelligence

Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy

Ayoub Kirouane +2 more

RoboticsArtificial Intelligence

TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model

Anqi Li +6 more

RoboticsArtificial IntelligenceComputer Vision and Pattern Recognition

RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?

Zhenxuan Fan +11 more

RoboticsComputer Vision and Pattern Recognition

CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements

Hongxiang Zhao +5 more

RoboticsComputer Vision and Pattern Recognition

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

AgiBot Research Team +44 more

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

Yuran Wang +23 more

RoboticsArtificial Intelligence

arXivSep 1

EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents

Wei Wang +16 more

Latent Action as Intention Enables Efficient Future Imagination for World Action Models

Xiang Li +12 more

arXivAug 16

GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture

GigaBrain Team +58 more

WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning

Chunkai Yang +2 more

Category

Computation and Language(10 papers)

Computation and LanguageMachine Learning

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Rongcan Pei +5 more

arXivSep 9

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

NCP Team +27 more

Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs

Seogyeong Jeong +5 more

Computation and LanguageArtificial IntelligenceMachine Learning

arXivSep 5

Steering Geometry: Validating Human Value Geometry in LLM Steering Space

Mohammad Mahdi Abootorabi +7 more

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

NeoHorse Team +36 more

Computation and LanguageMachine Learning

What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation

Daisuke Kikuta

Computation and LanguageMachine LearningMachine Learning

Unifying Conformal Language Tasks with In-Context Ensembles

Xiao Shi Huang +4 more

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

Alejo López-Ávila +4 more

arXivSep 1

Enoki: Efficient Multi-Level Hallucination Detection

Elisei Rykov +7 more

Computation and LanguageArtificial IntelligenceMachine Learning

Length-Adaptive Decoding for Masked Diffusion Machine Translation

Yan Zhan +3 more

Category

Sound(3 papers)

SoundArtificial Intelligence

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Haojun Zhang +9 more

SoundComputation and LanguageMultimedia

AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing

Ziyang Ma +32 more

SoundComputer Vision and Pattern RecognitionAudio and Speech Processing

arXivAug 28

Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue

Chengqian Ma +3 more

Cryptography and Security

Category

Cryptography and Security(3 papers)

arXivSep 5

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Nanxi Li +6 more

Cryptography and SecurityComputation and Language

CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

Jian Yang +10 more

Cryptography and SecurityArtificial Intelligence

arXivAug 21

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

Yibo Peng +3 more

Audio and Speech ProcessingComputer Vision and Pattern RecognitionSound

Category

Audio and Speech Processing(2 papers)

arXivAug 7

Training-Free Speech-Centric Omni Understanding with Frozen VLMs

Ankan Deria +4 more

Audio and Speech ProcessingArtificial IntelligenceMachine LearningMultimediaSound

Omni Interaction Agent Technical Report

Orantqing +22 more

Category

Optimization and Control(1 paper)

Optimization and ControlArtificial Intelligence

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

Sihan Ge +5 more

Category

Software Engineering(1 paper)

Software EngineeringArtificial IntelligenceComputation and Language

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

Tongyao Zhu +2 more

Category

Information Retrieval(1 paper)

arXivAug 13

DREAM Technical Report

Bin Zhang +76 more

Information Retrieval