3 papers
cs.LG2026
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
Song Lai, Haohan Zhao, Rong Feng +9
Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to ever-evolving downstream tasks. While exi…
cs.HC2026
From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions
Xiaolong Wang, Zhe Zhao, Song Lai +5
While LLMs show promise in automating educational content creation, their ability to generate questions that stimulate higher-order thinking remains understudied. This work evaluat…
cs.LG2025
Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off
Song Lai, Zhe Zhao, Fei Zhu +3
Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stabili…