Xuan He PRO

hexuan21's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 13 hours ago

LEV: Thinking Fast and Deep with Looped Decision Models

Paper • 2610.20951 • Published 8 days ago • 599

PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

Paper • 2610.21046 • Published 7 days ago • 545

upvoted 7 papers 3 days ago

Player-1: Learning to Play from Synthetic Experience

Paper • 2610.20584 • Published 8 days ago • 348

LensErase: A Foundation Model for Erase Anything

Paper • 2610.18072 • Published 8 days ago • 52

Hybrid Reasoning Agents

Paper • 2610.18861 • Published 9 days ago • 41

Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Paper • 2610.19366 • Published 8 days ago • 55

3DCodeVerse: Exploring 3D Worlds as Code

Paper • 2610.22341 • Published 7 days ago • 118

MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

Paper • 2610.20939 • Published 8 days ago • 150

OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

Paper • 2610.22200 • Published 7 days ago • 331

upvoted 3 papers 7 days ago

AgentGarten: Code Worlds for Evolving Agents

Paper • 2610.12374 • Published 14 days ago • 294

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

Paper • 2610.12572 • Published 14 days ago • 326

PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos

Paper • 2609.38377 • Published 23 days ago • 17

upvoted a paper 8 days ago

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published 14 days ago • 244

upvoted a paper 16 days ago

Post-Training Leaves Behavioral Shadows on Unrelated Decisions

Paper • 2609.29233 • Published 28 days ago • 274

upvoted a paper 18 days ago

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published 23 days ago • 34

upvoted 4 papers 22 days ago

Diffusion Reward Models

Paper • 2609.33803 • Published 25 days ago • 35

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published 24 days ago • 68

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published 25 days ago • 72

Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence

Paper • 2609.35432 • Published 24 days ago • 113

upvoted a paper about 1 month ago

Self-Distilled RLVR

Paper • 2604.03128 • Published Apr 3 • 147