Yulin Wang (王语霖)   Ph.D. Department of Automation, Tsinghua University Email: yulin-wang@tsinghua.edu.cn yulin.bh@gmail.com [Google Scholar] [ORCID] [Semantic Scholar] [Scopus]

Short Bio

Yulin Wang received his Ph.D. degree in the Department of Automation at Tsinghua University in 2025, advised by Prof. Gao Huang and Prof. Cheng Wu. Before that, he received his B.E. degree in Automation at Beihang University in 2019. He was a research intern at Berkeley DeepDrive, U.C. Berkeley, in 2018.

His research focuses on addressing the challenges of computational efficiency and data efficiency in building large-scale AI foundation models (e.g., visual/multi-modal foundation models, generative models, and embodied foundation models for robotics). He is also interested in developing new AI-based methods for addressing challenging scientific problems (e.g., medicine and geophysics), especially from the perspective of vision-language foundation models.

News (scroller)

[2025.10] AdaGen is Accepted by TPAMI. Check it out on GitHub.
[2025.09] Our newest work on dynamic neural networks, AdaptiveNN, is Accepted by Nature Machine Intelligence (5-year IF=31.8). [GitHub]
[2025.09] Two Papers are Accepted by NeurIPS 2025 (with one spotlight).
[2025.07] UltraBot is Accepted by Nature Communications (5-year IF=17.2). [Demo] [GitHub]
[2025.06] Two Papers are Accepted by ICCV 2025.
[2025.02] Four Papers are Accepted by CVPR 2025 (with one highlight).
[2024.12] Uni-AdaFocus is Accepted by TPAMI. Check it out on GitHub.
[2024.10] The Journal Version of InfoPro is Accepted by IJCV.
[2024.09] Two Papers are Accepted by NeurIPS 2024.
[2024.07] One Paper is Accepted by ECCV 2024.
[2024.05] EfficientTrain++ is Accepted by TPAMI. Check it out on GitHub.
[2024.02] One Paper is Accepted by CVPR 2024.
[2024.02] One Paper on Long-Tailed Visual Recognition is Accepted by TPAMI.
[2023.11] One Paper is Accepted by IJCV.
[2023.10] Awarded the National Scholarship.
(国家奖学金, 4th time, Top 2% in Tsinghua University)
[2023.07] Five Papers are Accepted by ICCV 2023.
[2022.10] Winning the 2022 ByteDance Scholarship.
(字节跳动奖学金, 10 PhD students in China)
[2022.09] Winning the 2022 Microsoft Research Asia Fellowship Award.
(“微软学者”奖学金, 12 PhD students in the Asia-Pacific region)
[2022.07] The Journal Version of GFNet is Accepted by TPAMI.
[2022.03 & 2022.07] AdaFocusV2 & AdaFocusV3 are Accepted by CVPR 2022 & ECCV 2022, respectively.
[2021.12] Winning the 2021 Baidu Scholarship.
(百度奖学金, 10 PhD students worldwide)
[2021.10] Awarded the National Scholarship.
(国家奖学金, 3rd time, Top 2% in Tsinghua University)
[2021.10] Winning the 2021 CCF-CV Outstanding Young Researcher Award.
(CCF-CV学术新锐奖, 3 PhD or Master students in China)
[2021.09] Not All Images are Worth 16x16 Words! Our Dynamic ViT (DVT) is Accepted by NeurIPS 2021.
[2021.09] Our Survey on Dynamic Neural Networks is Accepted by TPAMI.
[2021.07] AdaFocus is Accepted by ICCV 2021 for Oral Presentation.
[2021.05] Selected to be an Outstanding Reviewer of CVPR 2021.
[2021.03] Three Papers are Accepted by CVPR 2021 (with one Oral).
[2021.01] The Journal Version of ISDA is Accepted by TPAMI.
[2021.01] One Paper is Accepted by ICLR 2021.

Publications

2025

• Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
  Yulin Wang, Yang Yue (乐洋), Yang Yue (乐阳), Huanqian Wang, Haojun Jiang, Yizeng Han, Zanlin Ni, Yifan Pu, Minglei Shi, Rui Lu, Qisen Yang, Andrew Zhao, Zhuofan Xia, Shiji Song, Gao Huang
  Nature Machine Intelligence (5-year IF=31.8), 2025
  [arXiv] [Code] [清华自动化新闻 Tsinghua DA News]
• Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition
  Yulin Wang, Haoji Zhang, Yang Yue, Shiji Song, Chao Deng, Junlan Feng, Gao Huang
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
  [Code] [机器之心]
• AdaGen: Learning Adaptive Policy for Image Synthesis
  Zanlin Ni*, Yulin Wang*, Yeguo Hua, Renping Zhou, Jiayi Guo, Jun Song, Bo Zheng, Gao Huang
  [*co-first author, supervising Zanlin Ni (junior PhD student)]
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
  [Code]
• Towards Expert-level Autonomous Carotid Ultrasonography with Large-scale Learning-based Robotic System
  Haojun Jiang, Andrew Zhao, Qian Yang, Xiangjie Yan, Teng Wang, Yulin Wang, Ning Jia, Jiangshan Wang, Guokun Wu, Yang Yue, Shaqi Luo, Huanqian Wang, Ling Ren, Siming Chen, Pan Liu, Guocai Yao, Wenming Yang, Shiji Song, Xiang Li, Kunlun He, Gao Huang
  Nature Communications (5-year IF=17.2), 2025
  [Code] [Demo] [Poster] [HiT Webinar Talk] [清华新闻 Tsinghua News] [清华自动化新闻 Tsinghua DA News]
  [北京智源报道 BAAI News] [医工学人报道 Medical & Engineering Innovators] [CVer 报道]
• UltraSeP: Sequence-aware Pre-training for Echocardiography Probe Movement Guidance
  Haojun Jiang, Teng Wang, Zhenguo Sun, Yulin Wang, Yang Yue, Yu Sun, Ning Jia, Meng Li, Shaqi Luo, Shiji Song, Gao Huang
  Pattern Recognition (PR), 2025
  
• EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance
  Yang Yue*, Yulin Wang*, Haojun Jiang, Pan Liu, Shiji Song, Gao Huang
  [*co-first author, supervising Yang Yue (junior PhD student)]
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  [Code]
• CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
  Yang Yue*, Yulin Wang*, Chenxin Tao, Pan Liu, Shiji Song, Gao Huang
  [*co-first author, supervising Yang Yue (junior PhD student)]
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  [Code]
• XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?
  Fengxiang Wang, Hongzhen Wang, Zonghao Guo, Di Wang, Yulin Wang, Mingshuo Chen, Qiang Ma, Long Lan, Wenjing Yang, Jing Zhang, Zhiyuan Liu, Maosong Sun
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Highlight), 2025
  [Code]
• Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
  Jiayi Guo, Junhao Zhao, Chaoqun Du, Yulin Wang, Chunjiang Ge, Zanlin Ni, Shiji Song, Humphrey Shi, Gao Huang
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  [Code]
• GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
  Fengxiang Wang, Mingshuo Chen, Yueying Li, Di Wang, Haotian Wang, Zonghao Guo, Zefan Wang, Boqi Shan, Long Lan, Yulin Wang†, Hongzhen Wang†, Wenjing Yang†, Bo Du, Jing Zhang†
  [†corresponding authors]
  Advances in Neural Information Processing Systems (NeurIPS Spotlight), 2025
  [Code]
• RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
  Fengxiang Wang, Yulin Wang, Di Wang, Haotian Wang, Mingshuo Chen, Hongzhen Wang, Haiyan Zhao, Yangang Sun, Shuo Wang, Long Lan, Wenjing Yang, Jing Zhang
  Advances in Neural Information Processing Systems (NeurIPS), 2025
  [Code]
• IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
  Jiayi Guo, Chuanhao Yan, Xingqian Xu, Yulin Wang, Kai Wang, Gao Huang, Humphrey Shi
  IEEE/CVF International Conference on Computer Vision (ICCV), 2025
  [Code]
  
• LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
  Feihong Yan, Qingyan Wei, Jiayi Tang, Jiajun Li, Yulin Wang, Xuming Hu, Huiqi Li, Linfeng Zhang
  IEEE/CVF International Conference on Computer Vision (ICCV), 2025
  [Code]
  

2024

• EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
  Yulin Wang, Yang Yue, Rui Lu, Yizeng Han, Shiji Song, Gao Huang
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
  [Code] [机器之心]
• InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation
  Yulin Wang, Zanlin Ni, Yifan Pu, Cai Zhou, Jixuan Ying, Shiji Song, Gao Huang
  International Journal of Computer Vision (IJCV), 2024
  [Code]
• Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
  Chaoqun Du, Yulin Wang, Shiji Song, Gao Huang
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
  [Code] [机器之心]
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
  Yang Yue*, Yulin Wang*, Bingyi Kang, Yizeng Han, Shenzhi Wang, Shiji Song, Jiashi Feng, Gao Huang
  [*co-first author, supervising Yang Yue (junior PhD student)]
  Advances in Neural Information Processing Systems (NeurIPS), 2024
  [Code] [量子位]
• ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
  Zanlin Ni*, Yulin Wang*, Renping Zhou, Yizeng Han, Jiayi Guo, Zhiyuan Liu, Yuan Yao, Gao Huang
  [*co-first author, supervising Zanlin Ni (junior PhD student)]
  Advances in Neural Information Processing Systems (NeurIPS), 2024
  [Code]
• AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
  Zanlin Ni*, Yulin Wang*, Renping Zhou, Rui Lu, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Yuan Yao, Gao Huang
  [*co-first author, supervising Zanlin Ni (junior PhD student)]
  European Conference on Computer Vision (ECCV), 2024
  [Code] [机器之心]
• Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
  Zanlin Ni*, Yulin Wang*, Renping Zhou, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Shiji Song, Yuan Yao, Gao Huang
  [*co-first author, supervising Zanlin Ni (junior PhD student)]
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
  [Code]
• Rethinking the Architecture Design for Efficient Generic Event Boundary Detection
  Ziwei Zheng, Zechuan Zhang, Yulin Wang, Shiji Song, Gao Huang, Le Yang
  ACM International Conference on Multimedia (ACM MM), 2024
  [Code]
  

2023

• Glance and Focus Networks for Dynamic Visual Recognition
  Gao Huang*, Yulin Wang*, Kangchen Lv, Haojun Jiang, Wenhui Huang, Pengfei Qi, Shiji Song
  [*co-first author with my advisor]
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
  [Code] [知乎 (on GFNet)]
  
• Adapting Across Domains via Target-Oriented Transferable Semantic Augmentation Under Prototype Constraint
  Mixue Xie, Shuang Li, Kaixiong Gong, Yulin Wang, Gao Huang
  International Journal of Computer Vision (IJCV), 2023
  [Code]
• Fine-grained Recognition with Learnable Semantic Data Augmentation
  Yifan Pu, Yizeng Han, Yulin Wang, Junlan Feng, Chao Deng, Gao Huang
  IEEE Transactions on Image Processing (TIP), 2023
  
• Dynamic Spatial Focus for Efficient Compressed Video Action Recognition
  Ziwei Zheng, Le Yang, Yulin Wang, Miao Zhang, Lijun He, Gao Huang, Fan Li
  IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023
  
• Computation-efficient Deep Learning for Computer Vision: A Survey
  Yulin Wang, Yizeng Han, Chaofei Wang, Shiji Song, Qi Tian, Gao Huang
  Cybernetics and Intelligence (sponsored by the Department of Automation, Tsinghua University -- 清华自动化主办), 2023
  
• EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
  Yulin Wang, Yang Yue, Rui Lu, Tianjiao Liu, Zhao Zhong, Shiji Song, Gao Huang
  IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  [Code]
  
• Deep Incubation: Training Large Models by Divide-and-Conquering
  Zanlin Ni*, Yulin Wang*, Jiangwei Yu, Haojun Jiang, Yue Cao, Gao Huang
  [*co-first author, supervising Zanlin Ni (junior PhD student)]
  IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  [Code]
  
• Dynamic Perceiver for Efficient Visual Recognition
  Yizeng Han, Dongchen Han, Zeyu Liu, Yulin Wang, Xuran Pan, Yifan Pu, Chao Deng, Junlan Feng, Shiji Song, Gao Huang
  IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  [Code]
  
• Adaptive Rotated Convolution for Rotated Object Detection
  Yifan Pu, Yiru Wang, Zhuofan Xia, Yizeng Han, Yulin Wang, Weihao Gan, Zidong Wang, Shiji Song, Gao Huang
  IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  [Code]
• Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning Paradigm
  Wenxuan Ma, Shuang Li, Jinming Zhang, Chi Harold Liu, Jingxuan Kang, Yulin Wang, Gao Huang
  IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  [Code]

2022

• Regularizing Deep Networks with Semantic Data Augmentation
  Yulin Wang, Gao Huang, Shiji Song, Xuran Pan, Yitong Xia, Cheng Wu
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
  [Code] [知乎] [新智元] [AI科技评论]
  
• 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 (TPAMI), 2022
  [智源社区] [机器之心-在线讲座] [Bilibili]
  
• Meta-Semi: A Meta-Learning Approach for Semi-Supervised Learning
  Yulin Wang, Jiayi Guo, Jiangshan Wang, Cheng Wu, Shiji Song, Gao Huang
  CAAI Artificial Intelligence Research (sponsored by CAAI -- 中国人工智能学会主办), 2022
  
• AdaFocus V3: On Unified Spatial-temporal Dynamic Video Recognition
  Yulin Wang, Yang Yue, Xinhong Xu, Ali Hassani, Victor Kulikov, Nikita Orlov, Shiji Song, Humphrey Shi, Gao Huang
  European Conference on Computer Vision (ECCV), 2022
  
• AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
  Yulin Wang, Yang Yue, Yuanze Lin, Haojun Jiang, Zihang Lai, Victor Kulikov, Nikita Orlov, Humphrey Shi, Gao Huang
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  [Code]
  
• Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation
  Wenxuan Ma, Jinming Zhang, Shuang Li, Chi Harold Liu, Yulin Wang, Wei Li
  ACM International Conference on Multimedia (ACM MM), 2022
  [Code]
  

2021

• Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
  Yulin Wang, Rui Huang, Shiji Song, Zeyi Huang, Gao Huang
  Advances in Neural Information Processing Systems (NeurIPS), 2021
  [Code] [知乎] [量子位] [AI科技评论]
  
• Adaptive Focus for Efficient Video Recognition
  Yulin Wang, Zhaoxi Chen, Haojun Jiang, Shiji Song, Yizeng Han, Gao Huang
  IEEE/CVF International Conference on Computer Vision (ICCV Oral), 2021
  [Code] [Poster] [知乎] [Bilibili]
  
• Revisiting Locally Supervised Learning: An Alternative to End-to-end Training
  Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang
  International Conference on Learning Representations (ICLR), 2021
  [Code] [Poster] [知乎] [PaperWeekly] [Bilibili]
  
• Transferable Semantic Augmentation for Domain Adaptation
  Shuang Li, Mixue Xie, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Wei Li
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Oral), 2021
  [Code]
  
• MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
  Shuang Li, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Feng Qiao, Xinjing Cheng
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
  [Code]
  
• CondenseNet V2: Sparse Feature Reactivation for Deep Networks
  Le Yang, Haojun Jiang, Ruojin Cai, Yulin Wang, Shiji Song, Gao Huang, Qi Tian
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
  [Code]
  

2020

• Collaborative Learning with Corrupted Labels
  Yulin Wang, Rui Huang, Gao Huang, Shiji Song, Cheng Wu
  Neural Networks (NN), 2020
  
• Glance and Focus: A Dynamic Approach to Reducing Spatial Redundancy in Image Classification
  Yulin Wang, Kangchen Lv, Rui Huang, Shiji Song, Le Yang, Gao Huang
  Advances in Neural Information Processing Systems (NeurIPS), 2020
  [Code] [Poster] [知乎] [AI科技评论]
  

2019

• Logistics-aware Manufacturing Service Collaboration Optimisation towards Industrial Internet Platform
  Yulin Wang, Yongping Zhang, Fei Tao, Tingyu Chen, Ying Cheng, Shunkun Yang
  International Journal of Production Research (IJPR), 2019
  
• Implicit Semantic Data Augmentation for Deep Networks
  Yulin Wang, Xuran Pan, Shiji Song, Hong Zhang, Cheng Wu, Gao Huang
  Advances in Neural Information Processing Systems (NeurIPS), 2019
  [Code] [Poster]
  

Selected Awards and Honors

• First Prize of Natural Science Award (3/5), China Society of Image and Graphics (CSIG), 2024
  (中国图象图形学学会自然科学一等奖)
• National Scholarship, Ministry of Education of China, 2023
  (国家奖学金, 4th time, Top 2% in Tsinghua University)
• ByteDance Scholarship, ByteDance Ltd., 2022
  (字节跳动奖学金, 10 PhD students in China)
• Microsoft Research Asia Fellowship Award, Microsoft Research Asia, 2022
  (“微软学者”奖学金, 12 PhD students in the Asia-Pacific region)
• “Li Yanda” Scholarship, Tsinghua University, 2022
  (李衍达励学基金, 4 PhD students in the Department of Automation, Tsinghua University)
• Baidu Scholarship, Baidu Inc., 2021
  (百度奖学金, 10 PhD students worldwide)
• CCF-CV Outstanding Young Researcher Award, China Computer Federation (CCF), 2021
  (CCF-CV学术新锐奖, 3 PhD or Master students in China)
• National Scholarship, Ministry of Education of China, 2021
  (国家奖学金, 3rd time, Top 2% in Tsinghua University)
• Outstanding Oral Presentation, Doctoral Students Forum, Tsinghua University, 2021
• Travel Award, NeurIPS, 2019
• “Shen Yuan” Medal, Beihang University, 2018
  (沈元奖章，Top 10 of 18,000+ undergraduate students in Beihang University)
• National Scholarship, Ministry of Education of China, 2018
  (国家奖学金, 2nd time, Top 2% in Beihang University)
• National Scholarship, Ministry of Education of China, 2017
  (国家奖学金, 1st time, Top 2% in Beihang University)
• “Gong Xin” Innovation Scholarship, Ministry of Industry and Information Technology of China, 2017
  (工信部创新奖学金, Top 1/231 in Beihang University)
• First Prize in the “Zhou Peiyuan” Mechanics Competition for Undergraduate Students, 2017
  (全国周培源大学生力学竞赛一等奖, Top 0.3%)
• First Prize in National Undergraduate Mathematical Contest in Modeling, 2017
  (高教社杯全国大学生数学建模竞赛一等奖, Top 0.2%)
• Scholarship for Outstanding Academic Performance, Beihang University, 2016-2019
  (Top 5% in Beihang University)

Academic Service