Linxin Song PRO

linxinso's activity

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

upvoted a paper 13 days ago

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Paper • 2610.26828 • Published 16 days ago • 70

upvoted a paper 15 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 19 days ago • 49

upvoted a paper 19 days ago

Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL

Paper • 2610.21439 • Published 20 days ago • 29

authored a paper 23 days ago

Reflex: Visually Grounded Reactive Humanoid Control

Paper • 2610.12772 • Published 27 days ago • 48

upvoted a paper 23 days ago

Reflex: Visually Grounded Reactive Humanoid Control

Paper • 2610.12772 • Published 27 days ago • 48

updated a dataset 4 months ago

linxinso/OSWorld-SFT-results-20260714

Viewer • Updated Jul 14 • 20.8k • 5

published a dataset 4 months ago

linxinso/OSWorld-SFT-results-20260714

Viewer • Updated Jul 14 • 20.8k • 5

liked 5 datasets 4 months ago

nebius/SWE-rebench

Viewer • Updated Dec 23, 2025 • 27.9k • 55.7k • 78

nebius/SWE-agent-trajectories

Viewer • Updated Dec 23, 2024 • 80k • 14.5k • 105

SWE-bench/SWE-smith-trajectories

Viewer • Updated Jul 19, 2025 • 76k • 11.2k • 81

m-a-p/TerminalTraj

Viewer • Updated Feb 11 • 20k • 741 • 12

nvidia/Nemotron-Terminal-Corpus

Viewer • Updated Feb 27 • 366k • 22.5k • 150

updated a collection 6 months ago

Interesting paper

Collection

4 items • Updated May 5

upvoted 2 papers 6 months ago

Latent Collaboration in Multi-Agent Systems

Paper • 2511.20639 • Published Aug 3 • 131

GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction

Paper • 2604.23941 • Published Apr 27 • 6

upvoted a paper 7 months ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Paper • 2604.10577 • Published Apr 12 • 27

submitted a paper to Daily Papers 7 months ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Paper • 2604.10577 • Published Apr 12 • 27

upvoted 3 papers 7 months ago

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published Apr 9 • 86

Generative World Renderer

Paper • 2604.02329 • Published Apr 2 • 86

Steerable Visual Representations

Paper • 2604.02327 • Published Apr 2 • 55