AI.info

Rongzhi Zhang

Explore Rongzhi Zhang on AI.info.

• Rufus-Air: An Open LLM Post-Training Recipe
• HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
• Instant Personalized Large Language Model Adaptation via Hypernetwork