Gongxun Li

AlexGeek's activity

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

upvoted 2 papers 5 days ago

VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training

Paper • 2602.10693 • Published 16 days ago • 185

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Paper • 2602.08354 • Published 18 days ago • 211

upvoted a paper 14 days ago

The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies

Paper • 2602.09877 • Published 17 days ago • 197

upvoted a paper 17 days ago

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

Paper • 2602.08222 • Published 19 days ago • 271

upvoted a paper about 1 month ago

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published Jan 13 • 155