Lei Wang

demolei's activity

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

upvoted a paper 10 days ago

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

Paper • 2609.19969 • Published 11 days ago • 186

upvoted 2 papers 13 days ago

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

Paper • 2609.13287 • Published 19 days ago • 16

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 14 days ago • 247

upvoted 2 papers 19 days ago

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

Paper • 2609.04172 • Published 25 days ago • 102

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published 28 days ago • 174

upvoted a paper 22 days ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published 25 days ago • 246

upvoted 4 papers 25 days ago

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

Paper • 2608.31100 • Published 28 days ago • 42

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published 28 days ago • 169

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

Paper • 2609.01437 • Published 27 days ago • 221

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

Paper • 2609.02749 • Published 26 days ago • 403

upvoted a collection 25 days ago

MolmoWeb-Data

Collection

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

liked 4 datasets 25 days ago

Qwen/WebWorldData

Viewer • Updated May 8 • 463k • 473 • 79

webagentlab/webchain

Viewer • Updated about 1 month ago • 3.81k • 4.2k • 1

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

Viewer • Updated May 28, 2025 • 146k • 198 • 19

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

Viewer • Updated Mar 13 • 260k • 5.57k • 53

upvoted a paper 26 days ago

UI-Venus-2 Technical Report

Paper • 2609.00028 • Published Aug 27 • 65

upvoted 4 papers about 1 month 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 • 448

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

Paper • 2608.15763 • Published Aug 22 • 54

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

Paper • 2608.23041 • Published Aug 24 • 64

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

Paper • 2608.24876 • Published Aug 25 • 31