Ma

heurainbow's activity

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

upvoted a paper 3 days ago

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Paper • 2508.14460 • Published 4 days ago • 72

upvoted 2 papers 3 months ago

Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs

Paper • 2503.14286 • Published Mar 18 • 2

ShiQ: Bringing back Bellman to LLMs

Paper • 2505.11081 • Published May 16 • 2