Full Publications

A Lean Formalization of the Hamilton--Perelman Proof of Thurston's Geometrization Conjecture

Yuan Liao, Ziyang Qin, Jui-Hui Chung, Ayush Khaitan, Zhengyang Zhang, Hongzhou Lin, Zijian Zhang, Ligeng Zhu, Peng Lu, Bennett Chow

arXiv preprint, 2026

Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify

Zhengyang Zhang, Jing Xiong, Hongzhou Lin, Juihui Chung, Zijian Zhang, Song Han, Sihao Liu, Ligeng Zhu

arXiv preprint, 2026

Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits

Changye Li, Zijian Zhang, Muheng Li, Yiduo Pang, Tingjun Wu, Menghan Li, Yitong Liu, Hongkai Guo, Mengchi Chen, Chenyu He, Kaisheng Ma, Wei Xu, Song Han, Sihao Liu, Ligeng Zhu

arXiv preprint, 2026

Humanize: Judgement Engineering for Agentic Coding

Sihao Liu, Ligeng Zhu, Zijian Zhang, Dongyun Zou, Zhengyang Zhang, Changye Li, Song Bian, Song Han, Tony Nowatzki

arXiv preprint, 2026

EGM: Efficient Visual Grounding Language Models

Guanqi Zhan, Changye Li, Zhijian Liu, Yao Lu, Yi Wu, Song Han, Ligeng Zhu

European Conference on Computer Vision (ECCV), 2026

Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM

Chengyue Wu, Shiyi Lan, Yonggan Fu, Sensen Gao, Jin Wang, Jincheng Yu, Jose M Alvarez, Pavlo Molchanov, Ping Luo, Song Han, Ligeng Zhu, Enze Xie

arXiv preprint, 2026

Paper

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Haocheng Xi, Charlie Ruan, Peiyuan Liao, Yujun Lin, Han Cai, Yilong Zhao, Shuo Yang, Kurt Keutzer, Song Han, Ligeng Zhu

arXiv preprint, 2026

Paper

FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos

Yulu Gan, Ligeng Zhu, Dandan Shan, Baifeng Shi, Hongxu Yin, Boris Ivanovic, Song Han, Trevor Darrell, Jitendra Malik, Marco Pavone, Boyi Li

arXiv preprint, 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, Haotian Tang, Yunhao Fang, Yukang Chen, Cheng-Yu Hsieh, De-An Huang, An-Chieh Cheng, Jinyi Hu, Sifei Liu, Ranjay Krishna, Pavlo Molchanov, Jan Kautz, Hongxu Yin, Song Han, Yao Lu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Wolf: Dense Video Captioning with a World Summarization Framework

Boyi Li, Ligeng Zhu, Ran Tian, Shuhan Tan, Yuxiao Chen, Yao Lu, Yin Cui, Sushant Veer, Max Ehrlich, Jonah Philion, Xinshuo Weng, Fuzhao Xue, Linxi Fan, Yuke Zhu, Jan Kautz, Andrew Tao, Ming-Yu Liu, Sanja Fidler, Boris Ivanovic, Trevor Darrell, Jitendra Malik, Song Han, Marco Pavone

arXiv preprint, 2024

Paper

VILA²: VILA Augmented VILA

Yunhao Fang, Ligeng Zhu, Yao Lu, Yan Wang, Pavlo Molchanov, Jan Kautz, Jang Hyun Cho, Marco Pavone, Song Han, Hongxu Yin

arXiv preprint, 2024

Paper

PockEngine: Sparse and Efficient Fine-tuning in a Pocket

Ligeng Zhu, Lanxiang Hu, Ji Lin, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, Song Han

56th IEEE/ACM International Symposium on Microarchitecture (MICRO-56), 2023

Media coverage:

Tiny Machine Learning: Progress and Futures

Ji Lin, Ligeng Zhu, Wei-Ming Chen, Wei-Chen Wang, Song Han

IEEE Circuits and Systems Magazine, 2023

LIFT: Efficient Layer-wise Finetuning for Large Language Models

Ligeng Zhu, Lanxiang Hu, Ji Lin, Song Han

OpenReview manuscript, 2023

Paper

On-Device Training Under 256KB Memory

Ji Lin*, Ligeng Zhu*, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, Song Han

(* denotes equal contribution)

Advances in Neural Information Processing Systems (NeurIPS), 2022

Media coverage:

Laplacian of Logarithm as Illuminant-Invariant Input Space

Brian Funt, Ligeng Zhu

Color and Imaging Conference (CIC), 2022

Paper

Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications

Han Cai, Ji Lin, Yujun Lin, Zhijian Liu, Haotian Tang, Hanrui Wang, Ligeng Zhu, Song Han

ACM Transactions on Design Automation of Electronic Systems (TODAES), 2022

Paper

Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning

Ligeng Zhu, Hongzhou Lin, Yao Lu, Yujun Lin, Song Han

Advances in Neural Information Processing Systems (NeurIPS), 2021

IOS: Inter-Operator Scheduler for CNN Acceleration

Yaoyao Ding, Ligeng Zhu, Zhihao Jia, Gennady Pekhimenko, Song Han

Conference on Machine Learning and Systems (MLSys), 2021

Earlier title: Accelerate DNN Inference By Inter-Operator Parallelization.

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference

Zhijian Liu, Zhanghao Wu, Chuang Gan, Ligeng Zhu, Song Han

European Conference on Computer Vision (ECCV), 2020

Paper

TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning

Han Cai, Chuang Gan, Ligeng Zhu, Song Han

Advances in Neural Information Processing Systems (NeurIPS), 2020

Paper

AutoML for Architecting Efficient and Specialized Neural Networks

Han Cai, Ji Lin, Yujun Lin, Zhijian Liu, Kuan Wang, Tianzhe Wang, Ligeng Zhu, Song Han

IEEE Micro, 2019

Deep Leakage from Gradients

Ligeng Zhu, Zhijian Liu, Song Han

Advances in Neural Information Processing Systems (NeurIPS), 2019

Media coverage:

Zhihu

Distributed Training across the World

Ligeng Zhu, Yao Lu, Yujun Lin, Song Han

NeurIPS Workshop on Systems for ML (MLSys), 2019

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Han Cai, Ligeng Zhu, Song Han

International Conference on Learning Representations (ICLR), 2019

Media coverage:

Small Object Sensitive Segmentation of Urban Street Scene With Spatial Adjacency Between Object Classes

Dazhou Guo*, Ligeng Zhu*, Yuhang Lu, Hongkai Yu, Song Wang

(* denotes equal contribution)

IEEE Transactions on Image Processing (TIP), 2018

Paper

Paper

Colorizing Color Images

Ligeng Zhu, Brian Funt

Human Vision and Electronic Imaging (HVEI), 2018

Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering

Mengyao Zhai, Jiacheng Chen, Ruizhi Deng, Lei Chen, Ligeng Zhu, Greg Mori

arXiv preprint, 2017

Paper

Attribute Recognition from Adaptive Parts

Luwei Yang, Ligeng Zhu, Yichen Wei, Shuang Liang, Ping Tan

British Machine Vision Conference (BMVC), 2016

ZEST: Zeroshot Sparse Fine-tuning

Jiashu Han, Ligeng Zhu, Song Han

OpenReview manuscript

Paper

A Lean Formalization of the Hamilton--Perelman Proof of Thurston's Geometrization Conjecture

Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify

Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits

Humanize: Judgement Engineering for Agentic Coding

EGM: Efficient Visual Grounding Language Models

Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos

NVILA: Efficient Frontier Visual Language Models

Wolf: Dense Video Captioning with a World Summarization Framework

VILA²: VILA Augmented VILA

PockEngine: Sparse and Efficient Fine-tuning in a Pocket

Tiny Machine Learning: Progress and Futures

LIFT: Efficient Layer-wise Finetuning for Large Language Models

On-Device Training Under 256KB Memory

Laplacian of Logarithm as Illuminant-Invariant Input Space

Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications

Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning

IOS: Inter-Operator Scheduler for CNN Acceleration

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference

TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning

AutoML for Architecting Efficient and Specialized Neural Networks

Deep Leakage from Gradients

Distributed Training across the World

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Small Object Sensitive Segmentation of Urban Street Scene With Spatial Adjacency Between Object Classes

Does Colour Really Matter? Evaluation via Object Classification

Sparsely Aggregated Convolutional Networks

Colourization of Dichromatic Images

Colorizing Color Images

Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering

Attribute Recognition from Adaptive Parts

ZEST: Zeroshot Sparse Fine-tuning