Lei Wang

demolei's activity

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

upvoted a paper 2 days ago

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

Paper • 2603.23497 • Published 3 days ago • 84

upvoted a paper 4 days ago

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

Paper • 2603.22212 • Published 4 days ago • 121

upvoted a paper 5 days ago

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

Paper • 2603.17024 • Published 10 days ago • 104

upvoted 3 papers 6 days ago

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

Paper • 2603.18815 • Published 9 days ago • 14

Memento-Skills: Let Agents Design Agents

Paper • 2603.18743 • Published 9 days ago • 54

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

Paper • 2603.19220 • Published 8 days ago • 61

upvoted a paper 10 days ago

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

Paper • 2603.15726 • Published 11 days ago • 181

upvoted 3 papers 11 days ago

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

Paper • 2603.08127 • Published 19 days ago • 15

daVinci-Env: Open SWE Environment Synthesis at Scale

Paper • 2603.13023 • Published 15 days ago • 30

Attention Residuals

Paper • 2603.15031 • Published 12 days ago • 162

upvoted a paper 12 days ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published 15 days ago • 52

upvoted an article 13 days ago

view article

Article

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

• 
• 
• +7

18 days ago

•

79

upvoted a paper 17 days ago

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

Paper • 2603.09206 • Published 18 days ago • 52

upvoted a collection 17 days ago

MiroThinker-1.7

Collection

2 items • Updated 17 days ago • 53

upvoted 4 papers 21 days ago

On-Policy Self-Distillation for Reasoning Compression

Paper • 2603.05433 • Published 22 days ago • 6

Interactive Benchmarks

Paper • 2603.04737 • Published 23 days ago • 18

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

Paper • 2602.23166 • Published 29 days ago • 44

SkillNet: Create, Evaluate, and Connect AI Skills

Paper • 2603.04448 • Published 30 days ago • 91

upvoted 2 papers 22 days ago

Heterogeneous Agent Collaborative Reinforcement Learning

Paper • 2603.02604 • Published 25 days ago • 189

MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

Paper • 2603.03756 • Published 24 days ago • 89