每日论文 Daily Papers

来自 Hugging Face 与研究社区 · 中英对照

Daily Weekly Monthly

‹ 2026-11-02 ~ 2026-11-08 ›

跳转日期： 11-10 29 11-09 5 11-07 26 11-06 33 11-05 53 11-04 30 11-03 32 11-02 6 11-01 39 10-28 35 10-27 31 10-24 50 10-23 52 10-22 60 10-21 64 10-20 64 10-17 83 10-16 74 10-15 99 10-14 22 10-13 58 10-11 4 10-10 68 10-09 61 10-07 72 10-03 82 10-02 84 10-01 86 09-30 95 09-29 31

Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems

▲ 94 💬 1 ★ 8

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

▲ 80 💬 3 ★ 68

Words Caught in the Heart: Simulating Person-Specific Expression for Self-Opaque Clients in Psychotherapy

▲ 66 💬 1

Think Less, Locally: Local Preference Learning for Reasoning Compression

▲ 64 💬 6 ★ 2

R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop

▲ 61 💬 1

MoviEdit: Long-form Multi-Shot Video Editing Made Easy

▲ 60 💬 1 ★ 7

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

▲ 58 💬 1 ★ 30

CoworkOS:Scaling Agent Coworkers for Real-world Automation

▲ 56 💬 2 ★ 46

From Pixels to Actions - Towards Native Vision-Language-Action Policies

▲ 55 💬 2

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

▲ 54 💬 1 ★ 53

Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?

▲ 50 💬 1

Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling

▲ 48 💬 1

DreamX: Video Diffusion Model is a Universal Latent Action Learner

▲ 47 💬 1

Factorized MLLM Embeddings for Composed Image Retrieval

▲ 42 💬 1 ★ 7

RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild

▲ 42 💬 1 ★ 3

Axion 1.0: Open Agent Foundation Models, Simplified

▲ 38 💬 2 ★ 37

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

▲ 35 💬 1 ★ 7

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

▲ 34 💬 1 ★ 44

ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents

▲ 33 💬 1 ★ 7

GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling

▲ 33 💬 1 ★ 10

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

▲ 31

What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?

▲ 28 💬 2 ★ 2

YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction

▲ 26 💬 1

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

▲ 25 💬 1 ★ 14

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

▲ 24 💬 1

Wizard: Manipulate Any World in Real Time via Agentic Control

▲ 23 💬 1

Advances in Agentic Computer Graphics

▲ 23 💬 1

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

▲ 23 💬 2

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

▲ 23 💬 1 ★ 3

VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks

▲ 23 💬 1

EvoTeam: Multi-Agent Collaboration via Evolving Teams

▲ 23 💬 1

PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data

▲ 22 💬 2

HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model

▲ 21 💬 1

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

▲ 21 💬 1 ★ 2

Latent Reasoning in Continuous Space for Unified Multimodal Models

▲ 20 💬 1 ★ 2

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

▲ 20 💬 1 ★ 19

CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents

▲ 19 💬 1

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

▲ 19 💬 1 ★ 44

Halley: A Predictive Control Plane for Optical AI Data Center Networks

▲ 18 💬 1

StreamDuo: A Live Commentator and a Research Agent for Unseen Games

▲ 18 💬 2 ★ 1

CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems

▲ 17 💬 1 ★ 8

CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents

▲ 16 💬 1 ★ 32

ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost

▲ 16 💬 3

Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents

▲ 15 💬 1

MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery

▲ 15 💬 1

SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding

▲ 15 💬 1 ★ 82

Solv3R: 3D Looped Transformer as a Multi-view Solver

▲ 15 💬 2 ★ 111

Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use

▲ 14 💬 1

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

▲ 14 💬 2 ★ 1

Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs

▲ 13 💬 1 ★ 2

WorldBridge: Bridging Video and Action for Task Generalization in World Action Models

▲ 12 💬 1

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

▲ 12 💬 1 ★ 18

REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control

▲ 11 💬 1

ReLift: Dense 3D Tracking as Lifted Trajectory Repair

▲ 11 💬 4 ★ 1

Probing Spatial State Representations in Visual Foundation Models

▲ 11 💬 1

"Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents

▲ 11 💬 1 ★ 4

Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses

▲ 11 💬 1

VideoMemBench: How Well Do MLLMs Remember in Video Conversations?

▲ 11 💬 1 ★ 1

VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation

▲ 11 💬 1

Recursa: Toward Recursively Self-Improving Foundation Model Systems

▲ 10 💬 1

TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens

▲ 10 💬 1

MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation

▲ 10 💬 1

DecisionRank: On-Policy Distillation for Decision-Model Rerankers

▲ 9 💬 1

FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing

▲ 9 💬 1

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

▲ 9 💬 1

AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds

▲ 9 💬 1

Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation

▲ 8 💬 1 ★ 1

PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World

▲ 8 💬 1

SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding

▲ 8 💬 1 ★ 23

Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

▲ 7 💬 1 ★ 24

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

▲ 7 💬 2 ★ 1

Near-Zero Token Embeddings Silently Stall Training in Gated Sequence Models

▲ 7 💬 1

When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications

▲ 6 💬 1

HALO: Human-Grounded Granular Evaluation of Proactive Agents

▲ 6 💬 1 ★ 1

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

▲ 6 💬 1

Adversarial Speculative Reasoning Improves Long Horizon Agents

▲ 6 💬 1

Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?

▲ 6 💬 1 ★ 26

Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories

▲ 6 💬 1

LOLPlay: Benchmarking Real-Time Visual Agents in League of Legends

▲ 6 💬 1 ★ 4

Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents

▲ 6 💬 1 ★ 10

VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing

▲ 6 💬 2 ★ 7

LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers

▲ 6 💬 1 ★ 2

On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning

▲ 5 💬 1 ★ 2

RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory

▲ 5 💬 1

WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search

▲ 5 💬 1

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

▲ 5 💬 1 ★ 17

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

▲ 5 💬 4

You don't need long context

▲ 5 💬 2

SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?

▲ 5 💬 1

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

▲ 4 💬 1

Dory1.0-4B: A Looped Normalized-GPT

▲ 4 💬 1

RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On

▲ 4 💬 1

The SIMPLE Law for Energy Cost of LLM Inference

▲ 4 💬 1

How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates

▲ 4 💬 1 ★ 1

VeriSpoof: Beyond Real or Fake with One Audio LLM

▲ 4 💬 1 ★ 6

Supervising the Visible State: Separating Representation from View Selection in Streaming Video

▲ 3 💬 1

MemSteer: Turning User Histories into Supervision for Agent Memory Optimization

▲ 3 💬 1

GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching

▲ 3 💬 1 ★ 3

Measuring AI Agents as Teammates with Collaborative Intelligence

▲ 3 💬 1 ★ 15

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

▲ 3 💬 1 ★ 3

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

▲ 3 💬 1

Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena

▲ 3 💬 1 ★ 14

SeMo3D: Unifying 3D Generation, Editing, and Completion via Selective Modeling

▲ 3 💬 1 ★ 8

GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats

▲ 3 💬 1

NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers

▲ 3 💬 1 ★ 3

On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation

▲ 3 💬 2

CausalWAM: Learning the Causes of Actions in World Action Models

▲ 2 💬 1

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

▲ 2 💬 1 ★ 6

On-Policy Self-Distillation with Teacher Evolution

▲ 2 💬 1

ProVe: Proposer-Verifier Decoding

▲ 2 💬 1

BEND 2.0: Benchmarking the Capabilities Needed to Design DNA

▲ 2 💬 1 ★ 2

Muon Makes the First Mixture-of-Experts Layer Harder to Balance

▲ 2 💬 1

Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry

▲ 2 💬 1

Do We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG

▲ 2 💬 3 ★ 4

Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks

▲ 2 💬 1 ★ 8

What We Keep of What We Forget: Replacement Operators and Routing Semantics in Training-Free MoE Expert Pruning

▲ 2 💬 1

Is Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models

▲ 2 💬 1

Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents

▲ 2 💬 1

UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling

▲ 2 💬 2 ★ 2

Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting

▲ 2 💬 1

Follow the Gradient: Tracing Safety Degradation Back to Training Data

▲ 1 💬 1

rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment

▲ 1 💬 1

OSWAM: An Effective World Action Model with One-Step Action Generation

▲ 1 💬 1 ★ 20

Think Twice: The Metis-1.6 Technical Report

▲ 1 💬 1

Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling

▲ 1 💬 1

VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step

▲ 1 💬 1 ★ 85

SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World

▲ 1 💬 1 ★ 1

TernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation

▲ 1 💬 1 ★ 3

SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement

▲ 1 💬 1 ★ 2

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

▲ 1 💬 1

Can Large Language Model Agents Learn by Watching Tutorial Videos?

▲ 1 💬 1

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

▲ 1 💬 1 ★ 8

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

▲ 1 💬 1

Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks

▲ 1 💬 2

GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data

▲ 1 💬 1 ★ 1

Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction

▲ 1 💬 1

Going Deeper With Memories

▲ 1 💬 1

Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation

▲ 1 💬 1 ★ 6

LiveFoley: Dynamic Real-Time Video-to-Audio Generation for Immersive Interactive Worlds

▲ 1 💬 1

TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish

▲ 0 💬 1

No Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates

▲ 0 💬 1

LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

▲ 0 💬 1

TaoMate-FVSR:Audio-Guided Facial Video Restoration

▲ 0 💬 1 ★ 3

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

▲ 0 💬 1

Can Coding Agents Sustain Continual Evolution without Forgetting?

▲ 0 💬 1

QFabric: Guarded Cross-Domain Task Recovery and Its Limits on a Linux-RTOS Board

▲ 0 💬 1

Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention

▲ 0 💬 1

TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation

▲ 0 💬 1 ★ 10

HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias

▲ 0 💬 1 ★ 1

Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors

▲ 0 💬 1

Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization

▲ 0 💬 1

Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost

▲ 0 💬 1

DRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI

▲ 0 💬 1

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

▲ 0

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

EvoMemState: Evolving Memory State for Personal Agents

▲ 0

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

▲ 0

Towards Foundation Decision Models: Drex

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation

▲ 0

Future Representation Distillation for Imagination-free World Action Models

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

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

▲ 0

Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens

▲ 0

Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition

▲ 0

SynthFaces: Balanced Large Scale Human Dataset

▲ 0

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

▲ 0

Identically Trained Language Models Break on Different Jailbreaks

▲ 0