Lei Wang

demolei's activity

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

upvoted a paper 16 days ago

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

Paper • 2609.19969 • Published 17 days ago • 200

upvoted 2 papers 19 days ago

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

Paper • 2609.13287 • Published 25 days ago • 16

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 20 days ago • 251

upvoted 2 papers 25 days ago

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

Paper • 2609.04172 • Published about 1 month ago • 104

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 285

upvoted a paper 27 days ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published about 1 month ago • 248

upvoted 4 papers about 1 month ago

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

Paper • 2608.31100 • Published Aug 31 • 148

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 • 422

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

Paper • 2609.02749 • Published Sep 2 • 407

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

upvoted 9 papers about 1 month ago

UI-Venus-2 Technical Report

Paper • 2609.00028 • Published Aug 27 • 67

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 • 451

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 • 65

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

Paper • 2608.24876 • Published Aug 25 • 31

MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

Paper • 2608.23035 • Published Aug 24 • 42

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published Aug 24 • 212

Fara-1.5: Scalable Learning Environments for Computer Use Agents

Paper • 2606.20785 • Published Jun 18 • 9

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

Paper • 2608.17393 • Published Aug 18 • 26