Zhipeng Wang

Zhipeng Wang

ML researcher specialized in ML Systems, Multimodal Models and LLM post-training

Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction

Published in The Fourteenth International Conference on Learning Representations (ICLR 2026), 2026

Presented as a Poster at ICLR 2026.

Recommended citation: Ryan Lucas, Kayhan Behdin, Zhipeng Wang, Qingquan Song, Shao Tang, Rahul Mazumder. (2026). "Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction." ICLR 2026.
Download Paper