E2058

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

19 minutes ago

24m

E2057

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

29 minutes ago

19m

E2056

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

37 minutes ago

19m

E2055

SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

about 1 hour ago

15m

E2054

BadWAM: When World-Action Models Dream Right but Act Wrong

about 1 hour ago

21m

E2053

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

about 1 hour ago

22m

E2052

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

about 1 hour ago

20m

E2051

Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes

about 1 hour ago

21m

E2050

From Pixels to States: Rethinking Interactive World Models as Game Engines

about 1 hour ago

17m

E2049

UniVR: Thinking in Visual Space for Unified Visual Reasoning

about 2 hours ago

18m

E2048

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Jul. 17

19m

E2047

Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation

Jul. 17

19m

E2046

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

Jul. 17

20m

E2045

KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

Jul. 17

22m

E2044

OvisOCR2 Technical Report

Jul. 17

20m

E2043

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

Jul. 17

19m

E2042

MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

Jul. 17

18m

E2041

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

Jul. 17

21m

E2040

SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding

Jul. 16

20m

E2039

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Jul. 16

19m

E2038

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Jul. 16

19m

E2037

Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models

Jul. 16

19m

E2036

Weak-to-Strong Generalization via Direct On-Policy Distillation

Jul. 15

19m

E2035

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

Jul. 15

22m

E2034

4D Human-Scene Reconstruction from Low-Overlap Captures

Jul. 15

19m

E2033

LightMem-Ego: Your AI Memory for Everyday Life

Jul. 15

18m

E2032

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Jul. 14

20m

E2031

Scalable Visual Pretraining for Language Intelligence

Jul. 14

18m

E2030

Video Generation Models are General-Purpose Vision Learners

Jul. 14

20m

E2029

Vidu S1: A Real-Time Interactive Video Generation Model

Jul. 11

22m

E2028

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Jul. 11

24m

E2027

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks

Jul. 11

26m

E2026

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

Jul. 11

25m

E2025

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Jul. 10

26m

E2024

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

Jul. 10

25m

E2023

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Jul. 10

21m

E2022

Infinite Worlds with Versatile Interactions

Jul. 10

19m

E2021

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Jul. 9

25m

E2020

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Jul. 9

21m

E2019

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Jul. 9

20m

E2018

Vision as Unified Multimodal Generation

Jul. 9

26m

E2017

Gemma 4 Technical Report

Jul. 9

23m

E2016

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Jul. 8

20m

E2015

UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning

Jul. 8

21m

E2014

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

Jul. 8

23m

E2013

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Jul. 8

23m

E2012

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

Jul. 8

27m

E2011

MANCE: Manifold Aware Concept Erasure

Jul. 8

22m

E2010

GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation

Jul. 8

25m

E2009

Wan-Streamer v0.2: Higher Resolution, Same Latency

Jul. 8

21m

E2008

EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots

Jul. 8

22m

E2007

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Jul. 7

21m

E2006

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

Jul. 7

22m

E2005

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

Jul. 7

23m

E2004

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

Jul. 7

20m

E2003

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Jul. 7

22m

E2002

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Jul. 4

24m

E2001

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Jul. 4

23m

E2000

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Jul. 4

23m

E1999

Morphing into Hybrid Attention Models

Jul. 4

24m

E1998

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Jul. 4

21m

E1997

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

Jul. 4

22m

E1996

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Jul. 3

21m

E1995

Orca: The World is in Your Mind

Jul. 2

24m

E1994

Dockerless: Environment-Free Program Verifier for Coding Agents

Jul. 2

24m

E1993

DOPD: Dual On-policy Distillation

Jul. 2

25m

E1992

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

Jul. 2

21m

E1991

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

Jul. 2

23m

E1990

GEAR: Guided End-to-End AutoRegression for Image Synthesis

Jul. 2

26m

E1989

Multi-Block Diffusion Language Models

Jul. 2

23m

E1988

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Jul. 1

24m

E1987

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

Jul. 1

23m

E1986

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Jul. 1

26m

E1985

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Jul. 1

22m

E1984

Beyond IID: How General Are Tabular Foundation Models, Really?

Jul. 1

22m

E1983

Trimming the Long-Tail of Visual World Modeling Evaluation

Jul. 1

25m

E1982

AsyncOPD: How Stale Can On-Policy Distillation Be?

Jul. 1

22m

E1981

Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning

Jul. 1

20m

E1980

Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction

Jul. 1

22m

E1979

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Jun. 30

21m

E1978

Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots

Jun. 30

23m

E1977

Qwen-Image-2.0-RL Technical Report

Jun. 30

27m

E1976

DanceOPD: On-Policy Generative Field Distillation

Jun. 28

25m

E1975

In-Context World Modeling for Robotic Control

Jun. 28

23m

E1974

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

Jun. 28

21m

E1973

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Jun. 28

23m

E1972

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Jun. 28

22m

E1971

ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

Jun. 28

25m

E1970

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Jun. 28

20m

E1969

GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents

Jun. 28

23m

E1968

Fast LeWorldModel

Jun. 28

24m

E1967

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Jun. 13

24m

E1966

MiniMax Sparse Attention

Jun. 13

26m

E1965

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Jun. 13

22m

E1964

InterleaveThinker: Reinforcing Agentic Interleaved Generation

Jun. 13

21m

E1963

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Jun. 13

23m

E1962

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

Jun. 13

20m

E1961

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Jun. 13

23m

E1960

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

Jun. 13

20m

E1959

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

Jun. 13

23m