每日论文 Daily Papers

来自 Hugging Face 与研究社区 · 中英对照

Daily Weekly Monthly

‹ 2026-07-27 ~ 2026-08-02 ›

跳转日期： 09-11 30 09-09 10 09-08 26 09-07 31 09-04 31 09-03 26 08-30 2 08-29 21 08-28 32 08-27 23 08-26 32 08-25 21 08-23 11 08-21 33 08-19 59 08-18 31 08-15 30 08-14 23 08-11 30 08-07 47 08-06 36 08-05 37 08-04 25 08-02 38 07-31 17 07-30 23 07-29 27 07-28 16 07-25 21 07-24 19

AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

▲ 289 💬 2 ★ 7

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

▲ 277 💬 7

Metis: Memory Foundation Model

▲ 252 💬 3 ★ 51

Kimi K3: Open Frontier Intelligence

▲ 228 💬 4 ★ 2577

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

▲ 161 💬 2 ★ 91

PhiZero: A World Model Built Around Physical Language

▲ 155 💬 3 ★ 31

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

▲ 114 💬 1 ★ 64

JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents

▲ 98 💬 1 ★ 76

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

▲ 84 💬 1

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

▲ 71 💬 3 ★ 23

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

▲ 65 💬 2

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

▲ 64 💬 2 ★ 62

HumanCLAW: Can Vision-Language Models Act Through a Body?

▲ 63 💬 4 ★ 32

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

▲ 62 💬 1

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

▲ 57 💬 1

Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

▲ 54 💬 3 ★ 44

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

▲ 53 💬 2

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

▲ 49 💬 1

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

▲ 48 💬 2 ★ 7

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

▲ 46 💬 2 ★ 2

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

▲ 40 💬 1

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

▲ 40 💬 4

CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition

▲ 39 💬 1 ★ 1

Flux-OPD: On-Policy Distillation with Evolving Contexts

▲ 39 💬 2

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

▲ 37 💬 1 ★ 221

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

▲ 37 💬 2 ★ 3

ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine

▲ 34 💬 1

Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

▲ 30 💬 2 ★ 4

Data Pyramid for Embodied Manipulation

▲ 29 💬 1 ★ 62

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

▲ 28 ★ 18

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

▲ 27 💬 1 ★ 8

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

▲ 25 💬 2 ★ 3

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

▲ 23 💬 2

See2Think: Do Multimodal Models Really Use Intermediate Visual States?

▲ 22 💬 2 ★ 3

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

▲ 21 💬 1 ★ 1

SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them

▲ 21 💬 2 ★ 8

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

▲ 20 ★ 647

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

▲ 20 💬 1 ★ 52

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

▲ 19 💬 1

Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On

▲ 19 💬 1

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

▲ 17 💬 1 ★ 776

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

▲ 17 💬 1 ★ 3

β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

▲ 17 💬 2

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

▲ 16 💬 2 ★ 50

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

▲ 16 💬 1

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow

▲ 16 💬 3 ★ 20

Pass the Baton: Trajectory-Relayed On-Policy Distillation

▲ 15 💬 1 ★ 3

Can Large Language Models Execute Parent Orders?

▲ 14 💬 2 ★ 10

Scaling Native Multimodal Pre-Training From Scratch

▲ 13

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

▲ 13 💬 1 ★ 7

MemHarness: Memory Is Reconstructed, Not Replayed

▲ 13 💬 2 ★ 5

StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation

▲ 12 💬 1 ★ 1

Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems

▲ 12 💬 2 ★ 1

INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models

▲ 12 💬 3 ★ 71

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

▲ 11 💬 2 ★ 65

Three-Body Scattering for Generative Modeling

▲ 10 💬 1 ★ 29

LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger

▲ 10 💬 2

Wonder: Video World Model Done Better

▲ 9 💬 1

Can AI agents conduct open-ended AI research? Early evidence from two case studies

▲ 9

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

▲ 9 💬 2 ★ 13

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

▲ 8

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

▲ 8 💬 1 ★ 2

Multi-Head Attention Residuals

▲ 8 💬 3 ★ 5

▲ 7

PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models

▲ 7

Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking

▲ 7 💬 1 ★ 4

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

▲ 7 ★ 4

Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

▲ 6 💬 1 ★ 2

Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling

▲ 6 💬 2 ★ 8

dRAE: Representation Autoencoder with Hyper-Spherical Codes

▲ 6 💬 1 ★ 3

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

▲ 6 💬 2

DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes

▲ 5 💬 1

Parallel Decoding Distillation for Fast Image and Video Generation

▲ 5 💬 1 ★ 874

Visual prompt engineering for video models

▲ 5 💬 1

Explicit Layer Modeling for Video Object Insertion and Layer Decomposition

▲ 5 💬 1 ★ 4

IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

▲ 4 💬 1 ★ 7

SceneActBench: Can Agents Act on the 3D Scenes They See?

▲ 4 ★ 6

Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering

▲ 4

ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding

▲ 4 💬 1 ★ 4

Codifying the Judge: Scalable Evaluation via Program Distillation

▲ 4 💬 2 ★ 10

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

▲ 4 💬 1 ★ 16

GPT-Red: Automated Red Teaming via Self-Play at Scale

▲ 4

Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes

▲ 4 💬 2 ★ 2

Spectral Prior for Reducing Exposure Bias in Diffusion Models

▲ 3 💬 1

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation

▲ 3 ★ 2

A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever

▲ 3 💬 3 ★ 1

GNM Head: A Generative aNthropometric Model of the human head

▲ 3 ★ 1220

Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models

▲ 3 💬 1

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

▲ 3 💬 1

OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs

▲ 3

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

▲ 3 💬 1 ★ 2

Memory for Large Language Models

▲ 3 💬 1

Harness-G: A Graph-Structured Harness for Search Agents

▲ 3 💬 2 ★ 8

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models

▲ 3 💬 2 ★ 3

Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions

▲ 3 💬 2

AI Tour Meeting: Group Travel Planning by LLM Agents

▲ 3 💬 2

VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

▲ 2 💬 2 ★ 11

Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion

▲ 2 💬 1 ★ 3

Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization

▲ 2 💬 1

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

▲ 2 💬 1 ★ 2

CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation

▲ 2 💬 1

Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing

▲ 2 💬 2

ReToken: One Token to Improve Vision-Language Models for Visual Retrieval

▲ 2 💬 1 ★ 4

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

▲ 2 💬 3

Multimodal Speaker Verification as a Threat to Speaker Anonymization

▲ 1 💬 1 ★ 1

Interactive Training 2: Auditable Control Plane for Live Model Training

▲ 1 💬 1

Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels

▲ 1 💬 1

IndicTalk: A Large-Scale Persona-Based Multilingual Conversational Corpus for Indic Languages

▲ 1 💬 1

A Vocabulary for Multi-Agent Automated Research Systems

▲ 1 💬 1

VisualPatchWorld: Code World Models as Latent Structured Representations for Planning

▲ 1 💬 1 ★ 1

Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control

▲ 1 💬 1 ★ 1

Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems

▲ 1 💬 1 ★ 21

Characterizing Warp Divergence from Pascal to Blackwell

▲ 0 💬 1

DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification

▲ 0 💬 1

TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs

▲ 0 💬 1

GLI-AL: A Multi-Modal Glioma MRI Label Resource with Unified Anatomy-Lesion Labels

▲ 0 💬 1

Projection Pursuit CPCANet for Domain Generalization

▲ 0 💬 1

Edge-Aware Thermal Infrared UAV Swarm Tracking

▲ 0 💬 1

SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response

▲ 0 💬 1

AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition

▲ 0 💬 2

Pedestrian Archetypes Extension -- More Pedestrian Models for Autonomous Vehicle Safety Testing

▲ 0 💬 2