Zhijian Liu

I am an Assistant Professor at UC San Diego, where I direct Z Lab. I am also a Co-Founder and Chief Scientist at Inco AI. Previously, I was a Research Scientist at NVIDIA. I received my PhD from MIT, advised by Song Han.

My research focuses on making AI smaller, faster, and more efficient through full-stack innovations across algorithm, system, and application layers.

Openings

I am recruiting PhD students (HDSI/CSE) to work on efficient AI. Please apply through the program and mention my name in your application. I am also always looking for research interns. If you are interested, please fill out this form.

At Inco AI, we are building the inference stack end to end, and we are hiring. If you would like to work with us, write to talent@inco.ai.

News

5 papers accepted to ICLR 2026, including ParoQuant.
Selected as a Rising Star in Data Science by UChicago and UCSD.
Selected as a Rising Star in ML and Systems by MLCommons.
Awarded the Qualcomm Innovation Fellowship.

Selected Publications

DFlash: Block Diffusion for Flash Speculative Decoding

Jian Chen, Yesheng Liang, Zhijian Liu

ICML 2026

Paper Code Models

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Yesheng Liang, Haisheng Chen, Zihan Zhang, Song Han, Zhijian Liu

ICLR 2026

Paper Code Models

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

Jiaming Tang*, Yufei Sun*, Yilong Zhao, Shang Yang, Yujun Lin, Zhuoyang Zhang, James Hou, Yao Lu, Zhijian Liu, Song Han

Preprint

Paper Code

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference

Samir Khaki, Junxian Guo, Jiaming Tang, Shang Yang, Yukang Chen, Konstantinos N. Plataniotis, Yao Lu, Song Han, Zhijian Liu

ICCV 2025

Paper

NVILA: Efficient Frontier Visual Language Models

Zhijian Liu*, Ligeng Zhu*, Baifeng Shi, Zhuoyang Zhang, Yuming Lou, Shang Yang, Haocheng Xi, Shiyi Cao, Yuxian Gu, Dacheng Li, Xiuyu Li, Yunhao Fang, Yukang Chen, Cheng-Yu Hsieh, De-An Huang, An-Chieh Cheng, Vishwesh Nath, Jinyi Hu, Sifei Liu, Ranjay Krishna, Daguang Xu, Xiaolong Wang, Pavlo Molchanov, Jan Kautz, Hongxu Yin†, Song Han†, Yao Lu†

CVPR 2025

Paper Code