Hongbo Zhao

Continual learning methods for Video-LLMs face a fundamental trade-off: mitigating catastrophic forgetting often comes at the cost of generalization or prohibitive computational overhead.

Forget brute-force scaling: the secret to better educational AI agents lies in carefully structuring their roles, skills, and tools.

LLMs can gain 40% in knowledge transfer efficiency by mining skills from open-source agent repositories, without needing retraining.

Forget hand-engineered reward functions: this method uses language models to learn factorized world states that generalize to new goals and environments, outperforming LLM-as-a-Judge in zero-shot reward prediction.