Congliang Chen

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

AdaGC: Improving Training Stability for Large Language Model Pretraining

Prune, Then Select: Select High-Quality, Important, and Diverse Data Using Training Trajectories

Long CoT In-Context Learning Can Empower Pre-trained LLMs

Adam-mini: Use Fewer Learning Rates To Gain More

Preserving Diversity in Supervised Fine-Tuning of Large Language Models