ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
Paper • 2604.01591 • Published • 14
Difan Jiao
difanjiao
AI & ML interests
Generative Models & Mech Interp
Recent Activity
submitted a paper about 1 hour ago
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement liked a model 4 days ago
difanjiao/ThinkTwice-Qwen3-4B-Instruct updated a model 4 days ago
difanjiao/ThinkTwice-Qwen3-4B-InstructOrganizations
upvoted a paper 4 days ago
upvoted an article 5 months ago
Article
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
•
284