Tianzhu Ye

Experiential Learning outperforms traditional reinforcement learning by providing richer feedback, leading to better generalization and reduced reward hacking in LLM training.

By cleverly combining YOCO's efficient attention with recursive computation, YOCO-U achieves a capability-efficiency sweet spot that neither technique can reach on its own.

Language models can learn directly from real-world user interactions, boosting performance without human annotations or simulated environments.

Language models can now internalize experiential knowledge and system prompts more effectively through on-policy context distillation, leading to better task accuracy and out-of-distribution generalization.