Yimin Liu

yiminn's activity

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

upvoted a paper 3 days ago

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 5 days ago • 275

upvoted a paper 17 days ago

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

Paper • 2604.05172 • Published Apr 6 • 24

authored a paper 17 days ago

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Paper • 2609.19134 • Published 19 days ago • 101

upvoted a paper 17 days ago

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Paper • 2609.19134 • Published 19 days ago • 101

upvoted a paper about 1 month ago

Agentic Auto-Research is Fuzz Testing

Paper • 2608.09855 • Published Aug 10 • 7

New activity in benchflow/skillsbench-leaderboard 3 months ago

Add SkillsBench v1.1 agent-decouple integration matrix (7 ACP/decoupled agents x deepseek-v4-flash x with/without skill, docker; 1183 runs / 1014 healthy)

#16 opened 3 months ago by

yiminn

New activity in benchflow/skillsbench-leaderboard 4 months ago

Evidence archive: task.md-reformatted SkillsBench 87x3 (openhands + deepseek-v4-flash, 1 trial/condition, 261/261 healthy)

#13 opened 4 months ago by

yiminn

authored a paper 4 months ago

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

Paper • 2604.05172 • Published Apr 6 • 24

New activity in benchflow/skillsbench-leaderboard 5 months ago

PR3 OpenHands Chinese PR2-delta 6x3 matrix

#3 opened 5 months ago by

yiminn

Add SkillsBench useful trajectory snapshot

#2 opened 5 months ago by

yiminn

Add finished SkillsBench usable trajectories

1

#1 opened 5 months ago by

yiminn

liked a dataset 6 months ago

FayeZC/SkillMD-138K

Viewer • Updated Apr 8 • 138k • 213 • 5

upvoted a paper 7 months ago

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published Feb 13 • 67

authored a paper 8 months ago

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published Feb 13 • 67

updated a Space almost 3 years ago

Running

Test

🌖