Lei Wang

demolei's activity

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

upvoted a paper 1 day ago

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published 13 days ago • 299

upvoted a paper 7 days ago

WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

Paper • 2603.23497 • Published 9 days ago • 90

upvoted a paper 9 days ago

Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models

Paper • 2603.22212 • Published 10 days ago • 124

upvoted a paper 10 days ago

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published 16 days ago • 106

upvoted 3 papers 11 days ago

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

Paper • 2603.18815 • Published 14 days ago • 14

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published 14 days ago • 55

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published 14 days ago • 64

upvoted a paper 15 days ago

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

Paper • 2603.15726 • Published 17 days ago • 184

upvoted 3 papers 16 days ago

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

Paper • 2603.08127 • Published 24 days ago • 15

daVinci-Env: Open SWE Environment Synthesis at Scale

Paper • 2603.13023 • Published 20 days ago • 30

Attention Residuals

Paper • 2603.15031 • Published 17 days ago • 171

upvoted a paper 17 days ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published 21 days ago • 52

upvoted an article 18 days ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

23 days ago

•

91

upvoted a paper 22 days ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 23 days ago • 52

upvoted a collection 22 days ago

MiroThinker-1.7

Collection

2 items • Updated 22 days ago • 54

upvoted 4 papers 26 days ago

On-Policy Self-Distillation for Reasoning Compression

Paper • 2603.05433 • Published 28 days ago • 7

Interactive Benchmarks

Paper • 2603.04737 • Published 28 days ago • 18

AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

Paper • 2602.23166 • Published Feb 26 • 44

SkillNet: Create, Evaluate, and Connect AI Skills

Paper • 2603.04448 • Published Feb 26 • 91

upvoted a paper 27 days ago

Heterogeneous Agent Collaborative Reinforcement Learning

Paper • 2603.02604 • Published about 1 month ago • 191