3 papers
cs.LG2026
Constraint-Rectified Training for Efficient Chain-of-Thought
Qinhang Wu, Sen Lin, Ming Zhang +2
Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-t…
cs.LG2025
Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems
Hongbo Li, Qinhang Wu, Sen Lin +2
Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to spe…
cs.LG2025
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
Junze Deng, Qinhang Wu, Peizhong Ju +3
Rehearsal-based methods have shown superior performance in addressing catastrophic forgetting in continual learning (CL) by storing and training on a subset of past data alongside…