Gao Huang


Bio

I am an Associate Professor in the Department of Automation at Tsinghua University, where I lead the LEarning And Perception (LEAP) Lab. Previously, I was a postdoctoral researcher in the Department of Computer Science at Cornell University, working with Prof. Kilian Q. Weinberger. I received my PhD in machine learning from Tsinghua University in 2015.

My research interests lie at the intersection of machine learning and computer vision, with a particular focus on efficient foundation models. Specifically, I work on designing compact neural architectures and developing efficient training and inference algorithms for large-scale models, including large language models (LLMs), vision-language models (VLMs), and vision-language-action models (VLAs).

My research has been recognized by the Asian Young Scientist Fellowship (2024), MIT Innovators Under 35 Award (2021), DAMO Qingcheng Award (2020), and several research awards from academic communities and industry in China. I was also named among the AI2000 Most Influential Scholars in Computer Vision (2021). Our research has received the Best Paper Award at CVPR 2017 (DenseNet), was selected as a Best Paper Finalist at CVPR 2022 (Deformable Attention Transformer), and has won multiple Best Paper Awards at workshops, including NeurIPS 2018 and ICML 2025. Collectively, our work has garnered more than 85,000 citations according to Google Scholar. (C.V.)



For students who are interested in joining our lab (PhD/Master/Intern/Postdoc), please contact me via gaohuang AT tsinghua.edu.cn.


Professional Activities

  • Associate Editor, IEEE Transactions on Pattern Analysis and Machine Intelligence (2023-).
  • Associate Editor, IEEE Transactions on Big Data (2021-).
  • Associate Editor, Pattern Recognition (2022-).
  • Area Chair of NeurIPS(2025, 2023, 2022), CVPR(2026, 2022, 2021), ICCV(2025, 2023), ICML(2022), UAI(2022).
  • Senior Program Committee (SPC) member of AAAI (2018, 2020), IJCAI (2021).
  • Reviewer for JMLR, TPAMI, IJCV, Machine Learning, IJCV, TIP, TKDE, TNNLS, ...
  • Reviewer for NeurIPS, ICML, CVPR, ICCV, ECCV, AAAI, AISTATS, ...

Awards

  • Best Paper Award of ICML Workshop on AI4Math, 2025
  • Asian Young Scientist Fellowship, 2024
  • CVPR Best Paper Finalists, 2022
  • AI2000 Most Influential Scholar in Computer Vision, 2022
  • MIT TR 35 Asia-Pacific, MIT Technology Review, 2021
  • Research Fund for Outstanding Young Scholars, Nature Science Foundation of China, 2020
  • DAMO Qingcheng Award, Alibaba, 2020
  • Outstanding Young Researcher Award, Chinese Association for Artificial Intelligence, 2019
  • Zhiyuan Young Scholar, Beijing Academy of Artificial Intelligence (BAAI), 2019
  • Super AI Leader - Pioneer Award, World AI Conference (WAIC), 2018
  • NeurIPS Workshop Best Paper Award, 2018
  • CVPR Best Paper Award, 2017
  • Doctoral Dissertation Award, Chinese Association of Automation, 2015
Selected Conference Publications (Full Publication List on Google Scholar)

* Equal Contribution.

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? [code]
Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Shiji Song, Gao Huang.
International Conference on Machine Learning (ICML) Workshop on AI4Math (Best Paper Award) 2025.
Differential Transformer. [code]
Tianzhu Ye, Li Dong, Yuqing Xia, Yutao Sun, Yi Zhu, Gao Huang, Furu Wei.
International Conference on Learning Representations (ICLR Oral) 2025.
GridMix: Exploring Spatial Modulation for Neural Fields in PDE Modeling. [code]
Honghui Wang, Shiji Song, Gao Huang.
International Conference on Learning Representations (ICLR Oral) 2025.
Demystify Mamba in Vision: A Linear Attention Perspective. [code]
Dongchen Han, Ziyi Wang, Zhuofan Xia, Yizeng Han, Yifan Pu, Chunjiang Ge, Jun Song, Shiji Song, Bo Zheng, Gao Huang.
Neural Information Processing Systems (NeurIPS) 2024.
AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation. [code]
Zanlin Ni*, Yulin Wang*, Renping Zhou, Rui Lu, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Yuan Yao, Gao Huang.
European Conference on Computer Vision (ECCV) 2024.

Agent Attention: On the Integration of Softmax and Linear Attention. [code]
Dongchen Han*, Tianzhu Ye*, Yizeng Han, Zhuofan Xia, Shiji Song, Gao Huang.
European Conference on Computer Vision (ECCV) 2024.

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images. [code]
Ruyi Xu, Yuan Yao, Zonghao Guo, Junbo Cui, Zanlin Ni, Chunjiang Ge, Tat-Seng Chua, Zhiyuan Liu, Maosong Sun, Gao Huang.
European Conference on Computer Vision (ECCV) 2024.

Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels. [code]
Rui Huang, Songyou Peng, Ayca Takmaz, Federico Tombari, Marc Pollefeys, Shiji Song, Gao Huang, Francis Engelmann.
European Conference on Computer Vision (ECCV) 2024.

Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation. [code]
Shenzhi Wang*, Chang Liu*, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang.
Annual Meeting of the Association for Computational Linguistics (ACL Findings) 2024.

ExpeL: LLM Agents Are Experiential Learners. [code]
Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, Gao Huang.
AAAI Conference on Artificial Intelligence (AAAI Oral) 2024.

GSVA: Generalized Segmentation via Multimodal Large Language Models. [code]
Zhuofan Xia*, Dongchen Han*, Yizeng Han, Xuran Pan, Shiji Song, Gao Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024.
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models. [code]
Jiayi Guo*, Xingqian Xu*, Yifan Pu, Zanlin Ni, Chaofei Wang, Manushree Vasu, Shiji Song, Gao Huang, Humphrey Shi.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024.
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning. [code]
Shenzhi Wang*, Qisen Yang*, Jiawei Gao, Matthieu Gaetan Lin, Hao Chen, Liwei Wu, Ning Jia, Shiji Song, Gao Huang.
Neural Information Processing Systems (NeurIPS Spotlight) 2023.
Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL. [code]
Yang Yue*, Rui Lu*, Bingyi Kang*, Shiji Song, Gao Huang.
Neural Information Processing Systems (NeurIPS) 2023.
FLatten Transformer: Vision Transformer using Focused Linear Attention. [code]
Dongchen Han*, Xuran Pan*, Yizeng Han, Shiji Song, Gao Huang.
International Conference on Computer Vision (ICCV) 2023.
Adaptive Rotated Convolution for Rotated Object Detection. [code]
Yifan Pu*, Yiru Wang*, Zhuofan Xia, Yizeng Han, Yulin Wang, Weihao Gan, Zidong Wang, Shiji Song, Gao Huang.
International Conference on Computer Vision (ICCV) 2023.
Deep Incubation: Training Large Models by Divide-and-Conquering. [code]
Zanlin Ni*, Yulin Wang*, Jiangwei Yu, Haojun Jiang, Yue Cao, Gao Huang.
International Conference on Computer Vision (ICCV) 2023.
Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention. [code]
Xuran Pan*, Tianzhu Ye*, Zhuofan Xia, Shiji Song, Gao Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023.
Efficient Knowledge Distillation from Model Checkpoints. [code]
Chaofei Wang*, Qisen Yang*, Rui Huang, Shiji Song, Gao Huang.
Neural Information Processing Systems (NeurIPS Spotlight) 2022.
Provable General Function Class Representation Learning in Multitask Bandits and MDP.
Rui Lu, Andrew Zhao, Simon Shaolei Du, Gao Huang.
Neural Information Processing Systems (NeurIPS Spotlight) 2022.
Latency-aware Spatial-wise Dynamic Networks. [code]
Yizeng Han*, Zhihang Yuan*, Yifan Pu, Chenhao Xue, Shiji Song, Guangyu Sun, Gao Huang.
Neural Information Processing Systems (NeurIPS) 2022.
On the Integration of Self-Attention and Convolution. [code]
Xuran Pan, Chunjiang Ge, Rui Lu, Shiji Song, Guanfu Chen, Zeyi Huang, Gao Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022.
Vision Transformer with Deformable Attention. [code]
Zhuofan Xia*, Xuran Pan*, Shiji Song, Li Erran Li, Gao Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR Best Paper Finalist) 2022.
Assessing a Single Image in Reference-Guided Image Synthesis.
Jiayi Guo, Chaoqun Du, Jiangshan Wang, Huijuan Huang, Pengfei Wan, Gao Huang.
AAAI Conference on Artificial Intelligence (AAAI Oral) 2021.

Not All Images are Worth 16x16 Words: Dynamic Vision Transformers with Adaptive Sequence Length. [code]
Yulin Wang*, Rui Huang*, Shiji Song, Zeyi Huang, Gao Huang.
Neural Information Processing Systems (NeurIPS) 2021.
Adaptive Focus for Efficient Video Recognition. [code]
Yulin Wang*, Zhaoxi Chen*, Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang.
International Conference on Computer Vision (ICCV Oral) 2021.

3D Object Detection with Pointformer. [code]
Xuran Pan*, Zhuofan Xia*, Shiji Song, Li Erran Li, Gao Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021.
Revisiting Locally Supervised Learning: an Alternative to End-to-end Training. [code]
Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang.
International Conference on Learning Representations (ICLR) 2021.
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification. [code]
Yulin Wang, Kangchen Lv, Rui Huang, Shiji Song, Le Yang, Gao Huang.
Neural Information Processing Systems (NeurIPS) 2020.
Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation. [code]
Zhenda Xie, Zheng Zhang, Xizhou Zhu, Gao Huang , Stephen Lin.
European Conference on Computer Vision (ECCV Oral) 2020.
Asymmetric Valleys: Beyond Sharp and Flat Local Minima. [code] [slides]
Haowei He, Gao Huang, Yang Yuan.
Neural Information Processing Systems (NeurIPS Spotlight) 2019.
Implicit Semantic Data Augmentation for Deep Networks . [code]
Yulin Wang*, Xuran Pan*, Shiji Song, Hong Zhang, Cheng Wu, Gao Huang.
Neural Information Processing Systems (NeurIPS) 2019.

Rethinking the Value of Network Pruning. [code]
Zhuang Liu*, Mingjie Sun*, Tinghui, Zhou, Gao Huang, Trevor Darrell.
International Conference on Learning Representations (ICLR) 2019.
CondenseNet: An Efficient DenseNet using Learned Group Convolutions. [code] [talk]
Gao Huang*, Shichen Liu*, Laurens van der Maaten, Kilian Q. Weinberger.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR Spotlight) 2018.

Multi-Scale Dense Convolutional Networks for Resource Efficient Image Classification. [code]
Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Q. Weinberger.
International Conference on Learning Representations (ICLR Oral) 2018.

Memory-Efficient Implementation of DenseNets. [code1] [code2]
Geoff Pleiss*, Danlu Chen*, Gao Huang, Tongcheng Li, Laurens van der Maaten, Kilian Q. Weinberger.
Technical Report 2017.
Learning Efficient Convolutional Networks through Network Slimming. [code]
Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang.
International Conference on Computer Vision (ICCV) 2017.

Densely Connected Convolutional Networks. [code] [talk] [slides]
Gao Huang*, Zhuang Liu*, Laurens van der Maaten, Kilian Weinberger.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR Best Paper Award) 2017.

Snapshot Ensembles: Train 1, Get M for Free. [code]
Gao Huang*, Yixuan Li*, Geoff Pleiss, Zhuang Liu, John E. Hopcroft, Kilian Weinberger.
International Conference on Learning Representations (ICLR) 2017.
Supervised Word Mover's Distance. [code] [talk]
Gao Huang*, Chuan Guo*, Matt Kusner, Yu Sun, Fei Sha, Kilian Weinberger.
Neural Information Processing Systems (NIPS Oral) 2016.

Deep Networks with Stochastic Depth. [code] [poster] [talk]
Gao Huang*, Yu Sun*, Zhuang Liu, Daniel Sedra, Kilian Weinberger.
European Conference on Computer Vision (ECCV Spotlight) 2016.

(This paper was recommended as an Oral at NIPS 2016 Deep Learning Symposium)



Selected Journal Papers (Full Publication List on Google Scholar)

* Equal Contribution.

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training. [code]
Yulin Wang, Yang Yue, Rui Lu, Yizeng Han, Shiji Song, Gao Huang.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024.
Latency-aware Unified Dynamic Networks for Efficient Image Recognition. [code]
Yizeng Han*, Zeyu Liu*, Zhihang Yuan*, Yifan Pu, Chaofei Wang, Shiji Song, Gao Huang.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024.
Dynamic Neural Networks: Advantages and Challenges.
Gao Huang.
National Science Review (NSR), 2024.
Probabilistic Contrastive Learning for Long-Tailed Visual Recognition. [code]
Chaoqun Du, Yulin Wang, Shiji Song, Gao Huang.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024.
Glance and Focus Networks for Dynamic Visual Recognition. [code]
Gao Huang*, Yulin Wang*, Kangchen Lv, Haojun Jiang, Wenhui Huang, Pengfei Qi, Shiji Song.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2022.
Dynamic Neural Networks: A Survey.
Yizeng Han*,Gao Huang*, Shiji Song, Le Yang, Honghui Wang, Yulin Wang.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2021.
Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning.
Wenjie Shi, Gao Huang, Shiji Song, Cheng Wu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2021.
Regularizing Deep Networks with Semantic Data Augmentation. [code]
Yulin Wang*, Gao Huang*, Shiji Song, Xuran Pan, Yitong Xia, Cheng Wu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2021.
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning. [code]
Wenjie Shi, Gao Huang, Shiji Song, Zhuoyuan Wang, Tingyu Lin, Cheng Wu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2020.
Convolutional Networks with Dense Connectivity. [code]
Gao Huang, Zhuang Liu, Geoff Pleiss, Laurens Van Der Maaten, Kilian Q. Weingerger.
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2019.

(Journal version of DenseNet; Deep understanding of dense connectivity.)





Students

Contact

  • gaohuang at tsinghua dot edu dot cn
  • 617A Centre Main Building, Tsinghua University, Beijing 100084, China.