Xin Liu

xinliuthu's activity

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

upvoted 2 papers about 1 hour ago

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

Paper • 2611.03602 • Published 2 days ago • 26

CoworkOS:Scaling Agent Coworkers for Real-world Automation

Paper • 2611.03178 • Published 3 days ago • 96

upvoted 2 papers about 22 hours ago

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

Paper • 2610.22740 • Published 14 days ago • 46

ReLift: Dense 3D Tracking as Lifted Trajectory Repair

Paper • 2610.42136 • Published 5 days ago • 27

upvoted a paper 2 days ago

Training Foundation Models with a Single Algorithm

Paper • 2610.40564 • Published 7 days ago • 14

upvoted 3 papers 3 days ago

How Far Can Coding Agents Go in Visual Generation?

Paper • 2610.19025 • Published 23 days ago • 17

On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models

Paper • 2610.32770 • Published 13 days ago • 31

OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning

Paper • 2601.15351 • Published 13 days ago • 4

upvoted 2 papers 6 days ago

CodeCap-Bench: Can Code Serve as a Good Video Caption?

Paper • 2610.37341 • Published 9 days ago • 53

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Paper • 2610.34491 • Published 11 days ago • 22

upvoted a paper 9 days ago

Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

Paper • 2610.30866 • Published 14 days ago • 14

upvoted 2 papers 10 days ago

Can Visual Generation Expand What Unified Multimodal Models Know?

Paper • 2610.21459 • Published 21 days ago • 28

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

Paper • 2610.30926 • Published 14 days ago • 166

upvoted 2 papers 12 days ago

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

Paper • 2610.26659 • Published 17 days ago • 98

StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion

Paper • 2610.28940 • Published 16 days ago • 11

upvoted 2 papers 13 days ago

MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records

Paper • 2610.27911 • Published 16 days ago • 29

Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds

Paper • 2610.27999 • Published 16 days ago • 98

upvoted a paper 14 days ago

BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References

Paper • 2610.23986 • Published 22 days ago • 24

upvoted 2 papers 22 days ago

Less from More: Reinforcing Sparse Video Reasoning from Dense References

Paper • 2610.10893 • Published 29 days ago • 9

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

Paper • 2610.12341 • Published 28 days ago • 39