Zeliang Zhang

Diffusion models stubbornly cling to unwanted concepts, even when explicitly instructed to forget them, revealing a surprising weakness in instruction-based control.

Forget full-cache rollouts: this parameter-efficient fine-tuning method lets large reasoning models maintain accuracy while slashing memory usage during RL training.

Smaller vision-language models can punch above their weight in scientific domains like crystallography, given the right AI-generated open-book support.