Yibo Yang, Ph.D.

About Me

I am an Associate Professor at the School of Artificial Intelligence, Shanghai Jiao Tong University. I received my Ph.D. from Peking University in 2021, under the supervision of Prof. Zhouchen Lin. Prior to joining SJTU, I conducted research at JD Explore Academy, KAUST, and the University of Oxford.

Research Interests

My research aims to develop intelligent systems that can continuously learn and improve without forgetting previously acquired knowledge and capabilities, while remaining trustworthy and interpretable. Specifically, my research interests include, but are not limited to:

• Continual Learning and Self-Improving AI
• Interpretable and Trustworthy Machine Intelligence
• Interdisciplinary AI Research

News

Scroll for earlier updates ↓

Selected Publications

(*: equal contributions; #: corresponding author)

[Conference Papers]

• Mitigating Model Merging Conflicts via Knowledge-Aware Task Vector Purification
  Bang An, Yibo Yang#, Philip Torr, Bernard Ghanem
  Empirical Methods in Natural Language Processing, EMNLP 2026
  

• PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection
  Jinhan Liu, Yibo Yang, Ruiying Lu, Piotr Piekos, Yimeng Chen, Peng Wang, Dandan Guo
  Annual Meeting of the Association for Computational Linguistics, ACL 2026
  

• Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment
  Haozhong Wang, Zhuo Li, Yibo Yang, He Zhao, Hongyuan Zha, Dandan Guo
  Annual Meeting of the Association for Computational Linguistics, ACL 2026
  

• Benchmarking at the Edge of Comprehension
  Samuele Marro, Jialin Yu, Emanuele La Malfa, Oishi Deb, Jiawei Li, Yibo Yang, Ebey Abraham, Sunando Sengupta, Eric Sommerlade, Michael Wooldridge, Philip Torr
  International Conference on Machine Learning, ICML 2026, Oral Presentation
  

• A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
  Bingjie Zhang, Yibo Yang#, Renzhe, Dandan Guo#, Jindong Gu, Philip Torr, Bernard Ghanem
  International Conference on Learning Representations, ICLR 2026
  

• CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
  Zhongzhu Zhou, Fengxiang Bie, Ziyan Chen, Zhenyu Zhang, Yibo Yang, Junxiong Wang, Ben Athiwaratkun, Xiaoxia Wu, Shuaiwen Leon Song
  International Conference on Learning Representations, ICLR 2026
  

• Imitating the Truth: Attention-aware Truth-Guided Enhancement for Hallucination Mitigation in Large Vision-Language Models
  Hairui Ren, Zixuan Wang, Yibo Yang, He Zhao, Fan Tang, Dandan Guo, Yi Chang
  International Conference on Learning Representations, ICLR 2026
  

• Optimization-Inspired Few-Shot Adaptation for Large Language Models
  Boyan Gao#, Xin Wang, Yibo Yang#, David A. Clifton
  Advances in Neural Information Processing Systems, NeurIPS 2025, Spotlight Presentation
  

• Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
  Zitian Wang, Yue Liao#, Kang Rong, Fengyun Rao, Yibo Yang#, Si Liu
  International Conference in Computer Vision, ICCV, 2025
  

• Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
  Sihao Liu, Yibo Yang#, Xiaojie Li, David A. Clifton, Bernard Ghanem
  IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2025
  

• RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
  Shilin Xu, Haobo Yuan, Qingyu Shi, Lu Qi, Jingbo Wang, Yibo Yang, Yining Li, Kai Chen, Yunhai Tong, Bernard Ghanem, Xiangtai Li, Ming-Hsuan Yang
  International Conference on Learning Representations, ICLR 2025, Oral Presentation
  

• CorDA: Context-Oriented Decomposition Adaptation of Large Language Models
  Yibo Yang, Xiaojie Li, Zhongzhu Zhou, Shuaiwen Leon Song, Jianlong Wu, Liqiang Nie, Bernard Ghanem
  Advances in Neural Information Processing Systems, NeurIPS 2024
  [PDF] [Code by huggingface/peft (suggested)] [Code]
  Intro: We propose a new PEFT method with better performance on finetuning task and less forgetting of pre-trained world knowledge.

• GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning
  Xiaojie Li, Yibo Yang#, Xiangtai Li, Jianlong Wu#, Yue Yu, Bernard Ghanem, Min Zhang
  European Conference on Computer Vision, ECCV 2024
  [PDF] [Code]

• Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
  Yibo Yang, Xiaojie Li, Motasem Alfarra, Hasan Hammoud, Adel Bibi, Philip Torr, Bernard Ghanem
  International Conference on Machine Learning, ICML, 2024
  [PDF] [Code]

• Multi-Task Learning with Knowledge Distillation for Dense Prediction
  Yangyang Xu, Yibo Yang, Lefei Zhang
  IEEE/CVF International Conference in Computer Vision, ICCV, 2023
  [PDF]

• Understanding Imbalanced Semantic Segmentation Through Neural Collapse
  Zhisheng Zhong*, Jiequan Cui*, Yibo Yang*, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia
  IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2023
  [PDF] [Code]
  

• Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks
  Lingshen He, Yuxuan Chen, Zhengyang Shen, Yibo Yang, Zhouchen Lin
  International Conference on Learning Representations, ICLR 2023, Spotlight Presentation
  [PDF] [Code]

• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning
  Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, Dacheng Tao
  International Conference on Learning Representations, ICLR 2023, Spotlight Presentation
  [PDF] [Code]

• DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction
  Yangyang Xu, Yibo Yang, Lefei Zhang
  AAAI Conference on Artificial Intelligence, AAAI 2023
  [PDF] [Code]

• Towards Theoretically Inspired Neural Initialization Optimization
  Yibo Yang, Hong Wang, Haobo Yuan, Zhouchen Lin
  Advances in Neural Information Processing Systems, NeurIPS 2022
  [PDF] [Code]

• Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
  Yibo Yang, Shixiang Chen, Xiangtai Li, Liang Xie, Zhouchen Lin, Dacheng Tao,
  Advances in Neural Information Processing Systems, NeurIPS 2022
  [PDF] [Code]

• Eliminating Gradient Conflict in Reference-based Line-art Colorization
  Zekun Li, Zhengyang Geng, Zhao Kang, Wenyu Chen, Yibo Yang
  European Conference on Computer Vision, ECCV 2022
  [PDF] [Code]

• View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums
  Conghao Wong, Beihao Xia, Ziming Hong, Qinmu Peng, Wei Yuan, Qiong Cao, Yibo Yang, Xinge You
  European Conference on Computer Vision, ECCV 2022
  [PDF] [Code]

• Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation
  Xiangtai Li, Shilin Xu, Yibo Yang, Guangliang Cheng, Yunhai Tong, Dacheng Tao
  European Conference on Computer Vision, ECCV 2022
  [PDF] [Code]

• PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
  Haobo Yuan, Xiangtai Li, Yibo Yang#, Giangliang Cheng, Jing Zhang, Yunhai Tong, Lefei Zhang#, Dacheng Tao
  European Conference on Computer Vision, ECCV 2022
  [PDF] [Code]
  

  (The method in this paper also won the first place in Segmenting and Tracking Every Point and Pixel challenge in ICCV 2021)

• ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation
  Ruibin Wang, Yibo Yang#, Dacheng Tao
  IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2022
  [PDF] [Code]

• Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
  Yibo Yang, Shan You, Hongyang Li, Fei Wang, Chen Qian, Zhouchen Lin
  IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021
  [PDF]

• ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
  Yibo Yang, Hongyang Li, Shan You, Fei Wang, Chen Qian, Zhouchen Lin
  Advances in Neural Information Processing Systems, NeurIPS 2020
  [PDF] [Code]

• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
  Xia Li*, Yibo Yang*, Qijie Zhao, Tiancheng Shen, Zhouchen Lin, Hong Liu
  IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2020
  [PDF]

• SOGNet: Scene Overlap Graph Network for Panoptic Segmentation
  Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin
  AAAI Conference on Artificial Intelligence, AAAI 2020
  [PDF] [Code]
  (The method in this paper also won the Most Innovative Award in COCO 2019 challenge in ICCV 2019)

• Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families
  Yibo Yang, Jianlong Wu, Hongyang Li, Xia Li, Tiancheng Shen, Zhouchen Lin
  AAAI Conference on Artificial Intelligence, AAAI, 2020
  [PDF]

• Expectation-Maximization Attention Networks for Semantic Segmentation
  Xia Li, Zhisheng Zhong, Jianlong Wu, Yibo Yang, Zhouchen Lin, Hong Liu
  IEEE/CVF International Conference in Computer Vision, ICCV, 2019, Oral Presentation (4.3%)
  [PDF] [Code]

• Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-resolution
  Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang
  Advances in Neural Information Processing Systems, NeurIPS 2018
  [PDF]

• Optimization Algorithm Inspired Deep Neural Network Structure Design
  Huan Li*, Yibo Yang*, Dongmin Chen, Zhouchen Lin
  Asian Conference on Machine Learning, ACML 2018, Oral Presentation
  [PDF]

• Convolutional Neural Networks with Alternately Updated Clique
  Yibo Yang, Zhisheng Zhong, Tiancheng Shen, Zhouchen Lin
  IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Oral Presentation (2.1%)
  [PDF] [Code]
  (This paper also won the second place of the Most Popular Poster Award in VALSE 2018)

[Journal Papers]

• SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity
  Liyang Yuan, Yibo Yang, Dandan Guo, Peter Richtarik, Zhouchen Lin
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  

• Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
  Xiaojie Li, Yibo Yang, Jianlong Wu, Bernard Ghanem, Liqiang Nie, Min Zhang
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  

• ShadowNet for Data-Centric Quantum System Learning
  Yuxuan Du, Yibo Yang, Tongliang Liu, Zhouchen Lin, Bernard Ghanem, Dacheng Tao
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  

• DeGMix: Efficient multi-task dense prediction with deformable and gating mixer
  Yangyang Xu, Yibo Yang, Bernard Ghanem, Lefei Zhang, Bo Du, Jun Zhu
  IEEE Transactions on Circuits and Systems for Video Technology
  

• Task Prior Attention Network for Multi-Task Learning of Dense Prediction
  Yangyang Xu, Yibo Yang, Lefei Zhang, Bo Du
  SCIENCE CHINA Information Sciences
  

• Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
  Jiani Ni, He Zhao, Yibo Yang, Dandan Guo
  Pattern Recognition
  

• Starfish-Inspired Wearable Bioelectronic Systems for Physiological Signal Monitoring During Motion and Real-Time Heart Disease Diagnosis
  Sicheng Chen, Qunle Ouyang, Xianglin Meng, Yibo Yang, …, Bernard Ghanem, …
  Science Advances (Cover article in Science Advances Vol. 11, No. 14)
  [PDF]
  

• RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model
  Fengxiang Bie, Yibo Yang#, Zhongzhu Zhou, Adam Ghanem, Minjia Zhang, Zhewei Yao, Xiaoxia Wu, Connor Holmes, Pareesa Golnari, David A Clifton, Yuxiong He, Dacheng Tao, Shuaiwen Leon Song#
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  [PDF]
  

• PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation
  Xiangtai Li, Shilin Xu, Yibo Yang#, Haobo Yuan, Guangliang Cheng, Yunhai Tong#, Zhouchen Lin, Ming-Hsuan Yang, Dacheng Tao
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  [PDF]
  

• Towards open vocabulary learning: A survey
  Jianzong Wu, Xiangtai Li, Shilin Xu, Haobo Yuan, Henghui Ding, Yibo Yang, Xia Li, Jiangning Zhang, Yunhai Tong, Xudong Jiang, Bernard Ghanem, Dacheng Tao
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  [PDF]
  

• EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm
  Jiangning Zhang, Xiangtai Li, Yabiao Wang, Chengjie Wang, Yibo Yang, Yong Liu, Dacheng Tao
  International Journal of Computer Vision (IJCV)
  [PDF]
  

• Demystify Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification
  Yuxuan Du, Yibo Yang, Dacheng Tao, Min-Hsiu Hsieh
  Physical Review Letters
  [PDF]
  Intro: Inspired by neural collapse, we find out some provable advantages and limitations of the quantum neural network over the classical one.

• SFNet: Faster, Accurate, and Domain Agnostic Semantic Segmentation via Semantic Flow
  Xiangtai Li, Jiangning Zhang, Yibo Yang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Dacheng Tao
  International Journal of Computer Vision
  [PDF] [Code]
  

• Deformable medical image registration with global-local transformation network and region similarity constraint
  Xinke Ma, Hengfei Cui, Shuoyan Li, Yibo Yang, Yong Xia
  Computerized Medical Imaging and Graphics
  [PDF]
  

• Multi-task learning with multi-query transformer for dense prediction
  Yangyang Xu, Xiangtai Li, Haobo Yuan, Yibo Yang, Lefei Zhang
  IEEE Trans. Circuits and Systems for Video Technology
  [PDF]
  

• Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning
  Liang Xie, Yibo Yang, Deng Cai, Xiaofei He
  Neurocomputing
  [PDF]
  

• TransVOD: End-to-end Video Object Detection with Spatial-Temporal Transformers
  Qianyu Zhou, Xiangtai Li, Lu He, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lizhuang Ma, Dacheng Tao
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  [PDF] [Code]

• Improving Video Instance Segmentation via Temporal Pyramid Routing
  Xiangtai Li, Hao He, Yibo Yang, Henghui Ding, Kuiyuan Yang, Guangliang Cheng, Yunhai Tong, Dacheng Tao
  IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI)
  [PDF] [Code]

• Newton Design: Designing CNNs with the Family of Newton’s Methods
  Zhengyang Shen, Yibo Yang, Qi She, Jiwen Ma, Zhouchen Lin
  SCIENCE CHINA Information Sciences, (WOS Q1, CCF-A)
  [PDF]

• Optimization-Inspired Manual Architecture Design and Neural Architecture Search
  Yibo Yang, Zhengyang Shen, Huan Li, Zhouchen Lin
  SCIENCE CHINA Information Sciences, (WOS Q1, CCF-A)
  [PDF]

[Pre-prints]

• Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
  Yibo Yang, Sihao Liu, Chuan Rao, Bang An, Tiancheng Shen, Philip H.S. Torr, Ming-Hsuan Yang, Bernard Ghanem
  [PDF] [Code]
  

• Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
  Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, Dacheng Tao, Bernard Ghanem
  [PDF] [Code]
  Intro: An extended work of our ICLR’23 paper. We propose a unified method for continual learning under different data distribution.

Honors and Awards

• Stanford World’s Top 2% Scientists 2026/2025/2024
• [2025] Top 10% Area Chair for NeurIPS 2025
• [2025] Zuchongzhi Outstanding Achievement Award (“祖冲之奖”年度突出成果奖), 7/7
• [2024] Wuwenjun AI Science & Technology Award in CAAI (吴文俊人工智能科学技术奖), First Prize of Natural Science (自然科学一等奖), 5/5
• [2021] Wuwenjun Outstanding Ph.D. Dissertation Award in CAAI (中国人工智能学会优秀博士学位论文)
• [2021] First Place Winner of Video+Depth track in Segmenting and Tracking Every Point and Pixel (BMTT 2021 challenge) in ICCV 2021
• [2021] Outstanding Graduates in Beijing
• [2021] Outstanding Graduates in Peking University
• [2020] Presidential Fellowship in Peking University
• [2019] Outstanding Academic Award in Peking University
• [2019] Most Innovative Award of Panoptic Segmentation in COCO 2019 Challenge in ICCV 2019
• [2018] Runner-up Winner of Panoptic Segmentation in COCO 2018 Challenge in ECCV 2018
• [2018] Second Place Winner of Most Popular Poster Award in VALSE 2018 (top2 in 145)
• [2015] Finalist Award in American Interdisciplinary Contest in Modeling
• [2014] Provincial Merit Student in Jiangsu Province
• [2014] Second Prize in Jiangsu Provincial Advanced Mathematics Contest

Services

[Reviewer for Journals]

• Proceedings of the National Academy of Sciences of the United States of America (PNAS)
• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI);
• International Journal of Computer Vision (IJCV);
• IEEE Transactions on Neural Networks and Learning Systems (TNNLS);
• IEEE Transactions on Image Processing (TIP);

[Area Chair for Conferences]

• International Conference on Machine Learning (ICML), 2026
• Advances in Neural Information Processing Systems (NeurIPS), 2025/2024/2023
• International Conference on Learning Representations (ICLR), 2026/2025/2024
• International Conference on Artificial Neural Networks (ICANN), 2025/2024
• Association for the Advancement of Artificial Intelligence (AAAI), 2022

[Reviewer for Conferences]

• Advances in Neural Information Processing Systems (NeurIPS), 2022/2021/2020/2019;
• International Conference on Machine Learning (ICML), 2024/2023/2022/2021/2020;
• International Conference on Learning Representations (ICLR), 2023/2022/2021;
• European Conference on Computer Vision (ECCV), 2024/2022;
• International Conference on Computer Vision (ICCV), 2023/2021;
• IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024/2023/2022/2021;