Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 323
Lei Wang
demolei
AI & ML interests
LLMs
Recent Activity
Organizations
upvoted 3
papers 10 days ago
upvoted 4
papers 11 days ago
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
Paper • 2604.19859 • Published • 51
SWE-chat: Coding Agent Interactions From Real Users in the Wild
Paper • 2604.20779 • Published • 14
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 239
Mind DeepResearch Technical Report
Paper • 2604.14518 • Published • 23
upvoted 3
papers 13 days ago
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Paper • 2604.18292 • Published • 82
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
Paper • 2604.18224 • Published • 22
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
Paper • 2604.18543 • Published • 27
upvoted a paper 19 days ago
upvoted a paper 21 days ago
upvoted a paper 25 days ago
upvoted a paper 27 days ago
upvoted 6
papers about 1 month ago
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
Paper • 2603.28407 • Published • 70
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 349
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
Paper • 2603.23497 • Published • 91
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
Paper • 2603.22212 • Published • 126
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
Paper • 2603.17024 • Published • 109
ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
Paper • 2603.18815 • Published • 14