Chong Wang

Synthetic Bootstrapped Pretraining

On the Efficiency of Structured Pruning in Small Language Model Pretraining

Interleaved Reasoning for Large Language Models via Reinforcement Learning

Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo

Instruction-Following Pruning for Large Language Models

CommVQ: Commutative Vector Quantization for KV Cache Compression

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Fantastic Experts and How to Find Them: A Multi-Dimensional Study for Experts-Level Sparsification in Mixture-of-Experts