Zhe Cao

MichaelCaoo's activity

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

upvoted a paper about 8 hours ago

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

Paper • 2611.06910 • Published 3 days ago • 52

upvoted 3 papers 3 days ago

CoworkOS:Scaling Agent Coworkers for Real-world Automation

Paper • 2611.03178 • Published 4 days ago • 102

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

Paper • 2610.40191 • Published 8 days ago • 79

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

Paper • 2611.00859 • Published 7 days ago • 125

upvoted a collection 3 days ago

SolarWM

Collection

Family-specific checkpoints, released data, and paper for SolarWM long-horizon interactive video world models. • 7 items • Updated Sep 10 • 12

upvoted 2 papers 4 days ago

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

Paper • 2610.40799 • Published 9 days ago • 20

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

Paper • 2610.22740 • Published 16 days ago • 48

upvoted 2 papers 7 days ago

Your Benchmark Is an Empirical Measure Over Difficulty

Paper • 2610.29927 • Published 17 days ago • 26

VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team

Paper • 2610.33106 • Published 16 days ago • 26

upvoted 2 papers 9 days ago

ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

Paper • 2610.37666 • Published 11 days ago • 58

Hy-Nomas: Towards Free-form Interactive World Generation

Paper • 2610.36729 • Published 11 days ago • 113

upvoted a paper 12 days ago

Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs

Paper • 2610.27103 • Published 19 days ago • 17

upvoted 3 papers 15 days ago

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published Sep 1 • 88

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

Paper • 2610.26659 • Published 19 days ago • 99

Cache Engineering for Agents

Paper • 2610.28577 • Published 18 days ago • 104

upvoted a paper 17 days ago

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

Paper • 2610.26860 • Published 19 days ago • 102

upvoted a paper 19 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 23 days ago • 136

upvoted 2 papers 22 days ago

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Paper • 2610.18829 • Published 25 days ago • 54

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

Paper • 2610.19366 • Published 24 days ago • 50

upvoted a paper 23 days ago

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published Sep 30 • 92