Lei Wang

demolei's activity

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

upvoted a paper 10 days ago

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 17 days ago • 203

upvoted a paper 26 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 28 days ago • 229

upvoted 2 papers 29 days ago

LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents

Paper • 2609.13287 • Published Sep 9 • 16

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published about 1 month ago • 255

upvoted 7 papers about 1 month ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published Sep 3 • 104

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 287

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 212

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

Paper • 2608.31100 • Published Aug 31 • 149

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published Aug 31 • 274

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

Paper • 2609.01437 • Published Sep 1 • 569

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published Sep 2 • 408

upvoted a collection about 1 month ago

MolmoWeb-Data

Collection

This is the collection of all datasets in MolmoWebMix. • 6 items • Updated Mar 24 • 33

liked 4 datasets about 1 month ago

Qwen/WebWorldData

Viewer • Updated May 8 • 463k • 667 • 82

webagentlab/webchain

Viewer • Updated Aug 28 • 3.81k • 3.1k • 2

data-for-agents/insta-150k-v3

Viewer • Updated May 28, 2025 • 146k • 168 • 20

yatin-superintelligence/Edge-Agent-Reasoning-WebSearch-260K

Viewer • Updated Mar 13 • 260k • 4k • 54

upvoted a paper about 1 month ago

UI-Venus-2 Technical Report

Paper • 2609.00028 • Published Aug 27 • 67

upvoted 3 papers about 2 months ago

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published Aug 15 • 452

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

Paper • 2608.15763 • Published Aug 22 • 55

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Paper • 2608.23041 • Published Aug 24 • 66