Publications

* denotes equal contribution.

BLASST dynamically skips low-impact attention blocks

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding

Jiayi Yuan*, Cameron Shinn*, Kai Xu, Jingze Cui, George Klimiashvili, Guangxuan Xiao, Perkz Zheng, Bo Li, Yuxin Zhou, Zhouhai Ye, Weijie You, Tian Zheng, Dominic Brown, Pengbo Wang, Markus Hoehnerbach, Richard Cai, Julien Demouth, John D. Owens, Xia Hu, Song Han, Timmy Liu, Huizi Mao

Proceedings of Machine Learning and Systems (MLSys), 2026
Best Research Paper Award

Paper Blog BibTeX

Marigold diffusion fine-tuning protocol

Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis

Bingxin Ke*, Kevin Qu*, Tianfu Wang*, Nando Metzger*, Shengyu Huang, Bo Li, Anton Obukhov, Konrad Schindler

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

Paper Code Project BibTeX

Activation distributions before and after QuaRot

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman

Advances in Neural Information Processing Systems (NeurIPS), 2024

Paper Code BibTeX

Collision-aware actuated face simulation results

Efficient Incremental Potential Contact for Actuated Face Simulation

Bo Li*, Lingchen Yang*, Barbara Solenthaler

SIGGRAPH Asia Technical Communications, 2023

Paper Video Project BibTeX

Last edited: July 13, 2026