| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 12 Dec 2025 18:15:48 GMT
access-control-allow-origin: *
etag: W/"693c5bd4-1da69"
expires: Mon, 29 Dec 2025 00:01:35 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 735D:3827E5:8216EA:92168A:6951C27D
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 23:51:35 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210042-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766965895.144264,VS0,VE231
vary: Accept-Encoding
x-fastly-request-id: 23e3e46c93fea953a5f3e13e11a1d1e23ed45abe
content-length: 18482
Guangyi Chen's Homepage
2025-11: I have a wonderful visit to HongKong and give some talks on causal representation learning at HKU, CUHK, HKUST, and HKBU. Thanks so much to Prof. Yin Guosheng , Prof. Farzan Farnia , Prof. Raymond Wong , and Prof. Bo Han for their hosts.
2025-10: Excited to release CausalVerse, a NeurIPS 2025 Spotlight! 🎉
It’s the first comprehensive benchmark for causal representation learning with controllable, high-fidelity simulations.
Welcome to join us to make CRL practical and powerful:
Arxiv,
Project page,
Datasets, and
Code.
2025-09: 5 papers on causal representation learning, vision language model, and generative models are accepted by NeurIPS'2025.
2025-08: I give a talk at UCSD to discuss causal representation learning and trustworthy AI [slides], thanks Biwei for the invitation!
2025-08: 1 paper on causal representation learning is accepted by TPAMI.
2025-06: I give a talk at City University of Hong Kong, thanks Prof. Fenglei Fan for the invitation!
2025-05: 3 papers on demonstating causal representation learning and causal lens in Diffusion model, LLM, and domain adaptation are accepted by ICML'2025.
2025-04: I give talks at NTU and NUS to discuss causal representation in visual understaning [slides], thanks Prof. Dacheng Tao and Prof. Xiaokui Xiao for hosting me!
2025-03: SmartCLIP is selected as Highlight by CVPR'2025.
2025-02: IDOL is selected as Oral by ICLR'2025.
2025-02: 1 paper on casaul representation learning and CLIP model is accepted by CVPR'2025.
2025-01: 4 papers on casaul representation learning are accepted by ICLR'2025.
2025-01: 1 paper on casaul representation learning is accepted by WWW'2025.
World’s Top 2% Scientists, Stanford–Elsevier, 2025
Jiang Zhen Scholarship, Tsinghua University, 2020
2nd place in Semi-Supervised Recognition Challenge at FGVC7, CVPR, 2020
Samsung Scholarship, 2019
Academic Excellence Scholarship, Tsinghua University, 2015
Tsinghua Scholarship, Tsinghua University, 2014
National Encouragement Scholarship, Ministry of Education of P.R. China, 2014
National Encouragement Scholarship, Ministry of Education of P.R. China, 2013
TA Analog Electronic Technology Foundation, Tsinghua University, 2018.
TA Analog Electronic Technology Foundation, Tsinghua University, 2019.
TA Numerical Analysis and Algorithm, Tsinghua University, 2019.
TA Probabilistic and Statistical Inference (ML703), MBZUAI，2021, Fall.
TA Probabilistic and Statistical Inference (ML703), MBZUAI，2022, (Spring, Fall).
TA Advanced Probabilistic and Statistical Inference (ML803), MBZUAI，2023, (Spring, Fall).
TA Advanced Probabilistic and Statistical Inference (ML803), MBZUAI，2024, Spring.
Publicity Chair: for CLeaR 2023.
Area Chair: for ICLR 2026.
Co-organizer:
Conference Reviewer / Program Committee Member: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, and so on.
Journal Reviewer: TPAMI, TIP, IJCV, TNNLS, TMM, TCSVT, and so on.
About Me
I am a research scientist at Cargenie Mellon University (CMU) and MBZUAI. I currently co-lead the Causal Learning and Reasoning (CLeaR) Group with Prof. Kun Zhang . Prior to that, I received both my Ph.D. and B.S. degrees from Tsinghua University, advised by Prof. Jie Zhou and Prof. Jiwen Lu . My research interests include causality, representation learning, and computer vision. A central focus of my current work is to develop principled and practical methods for learning meaningful visual representations that support recognization, understanding, generation, and reasoning.
I’m currently on the academic job market! If you’re interested in my research and believe I could be a strong addition to your department, I’d be glad to connect. Please don’t hesitate to reach out by dropping me an e-mail guangyichen1994(at)gmail.com .
News
Research Topics
Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer
We present Tem-Adapter, a method that improves VQA by leveraging image-based knowledge and introducing temporal and semantic aligners.
Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction
We propose to formualte the sampling process with Baysesian optimization to promote stochasitic human trajectory prediction in an unsupervised manner.
Understanding Masked Autoencoders via Hierarchical Latent Variable Models
We propose a causal perspective to understand the underlying mechanism of MAE to identify latent variables in the hierarchical model.
GAIN: On the Generalization of Instructional Action Understanding
We present a benchmark, named GAIN, to analyze the generalizability of instructional action understanding models.
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion
We propose a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion.
Spatial-Temporal Attention-aware Learning for Video-based Person Re-identification
We propose a spatial-temporal attention to jointly discover the salient clues in both spatial and temporal domain.
Probabilistic Temporal Modeling for Unintentional Action Localization
We propose a probabilistic framework with dense predictions to allow the uncertainty of annotations for unintentional action localization.
Unintentional Action Localization via Counterfactual Examples
We propose to disentangle the effects of content and intention clues by building a counterfactual video pool and learning hidden causal processes contrastively.
FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment
We construct a new fine-grained dataset for the explainable action quality assessment, named FineDiving.
Human Trajectory Prediction via Counterfactual Analysis
We propose a counterfactual analysis method for human trajectory prediction to investigate the causality between the predictions and inputs, and alleviate the negative effects brought by environment bias.
Personalized Trajectory Prediction via Distribution Discrimination
We present a distribution discrimination (DisDis) method to predict personalized motion patterns by distinguishing the potential distributions in a self-supervised manner.
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification
We propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process.
Person Re-identification via Attention Pyramid
We propose attention pyramid networks by the "split-attend-merge-stack" principle to jointly learn the attentions under different scales.
Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?
We show temporal coherence plays a more critical role than temporal motion for video-based person ReID and develop an adversarial feature augmentation to highlight temporal coherence.
Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification
We propose to adaptively and progressively mine credible training samples to avoid the damage from the noise of predicted pseudo labels for unsupervised domain adaptation person ReID.
Self-Critical Attention Learning for Person Re-Identification
We present a self-critical attention learning method which applies a critic module to examine and supervise the attention model.
Prompt Learning with Optimal Transport for Vision-Language Models
we propose to learn multiple comprehensive prompts with optimal transport to adapt the pretrained vision-laguage model.
Adversarial Alignment for Source Free Object Detection
Adversarial Alignment proposes a variance-based criterion of detection to build pseudo supervisions for source free adaptative object detection.
DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
DenseCLIP is a new framework for dense prediction by implicitly and explicitly adapting the pre-trained knowledge from CLIP.
Temporally Disentangled Representation Learning
A framework to recover time-delayed latent causal variables and identify their relations from sequential data under stationary environments or different distribution shifts.
Partial Disentanglement for Domain Adaptation
A framework with partial identifiablity to minimize unnecessary influences of domain shift with minimal changes of causal mechanisms.Publications
Some selected recent publications. Please see Google Scholar for details.
- Yunlong Deng*, Guangyi Chen*, Tianpei Gu, Lingjing Kong, Yan Li, Zeyu Tang, Kun Zhang, Towards Self-Refinement of Vision-Language Models with Triangular Consistency, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2025. [Code]
- Guangyi Chen*, Yunlong Deng*, Peiyuan Zhu*, Yan Li*, Yifan Shen, Zijian Li, Kun Zhang, CausalVerse: A Comprehensive Benchmark for Causal Representation Learning with Controllable High-Fidelity Simulations, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2025 Spotlight. [Project Page] [Datasets] [Code]
- Zijian Li, Changze Zhou, Minghao Fu, Sanjay Manjunath, Fan Feng, Guangyi Chen, Yingyao Hu, Ruichu Cai, Kun Zhang, Online Time Series Forecasting with Theoretical Guarantees, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2025.
- Zijian Li, Minghao Fu, Junxian Huang, Yifan Shen, Ruichu Cai, Yuewen Sun, Guangyi Chen, Kun Zhang, Towards Identifiability of Hierarchical Temporal Causal Representation Learning, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2025.
- Jiayou Zhang, Yifan Shen, Guangyi Chen, Le Song, Eric P. Xing, Dimensional Collapse in VQVAEs: Evidence and Remedies, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2025.
- Shaoan Xie*, Lingjing Kong*, Yujia Zheng, Zeyu Tang, Eric P. Xing, Guangyi Chen, Kun Zhang, Learning Vision and Language Concepts for Controllable Image Generation, International Conference on Machine Learning (ICML), 2025.
- Zeyu Tang*, Zhenhao Chen*, Xiangchen Song, Loka Li, Yunlong Deng, Yifan Shen, Guangyi Chen, Peter Spirtes, Kun Zhang, Reflection-Window Decoding: Text Generation with Selective Refinement, International Conference on Machine Learning (ICML), 2025.
- Ignavier Ng*, Yan Li*, Zijian Li, Yujia Zheng, Guangyi Chen, Kun Zhang, A General Representation-Based Approach to Multi-Source Domain Adaptation, International Conference on Machine Learning (ICML), 2025.
- Shaoan Xie*, Lingjing Kong*, Yujia Zheng, Yu Yao, Zeyu Tang, Eric P. Xing, Guangyi Chen, Kun Zhang, SmartCLIP: Modular Vision-language Alignment with Identification Guarantees, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 Highlight.
- Yuewen Sun*, Lingjing Kong*, Guangyi Chen, Loka Li, Gongxu Luo, Zijian Li, Yixuan Zhang, Yujia Zheng, Mengyue Yang, Petar Stojanov, Eran Segal, Eric P Xing, Kun Zhang, Causal Representation Learning from Multimodal Biological Observations, The Thirteenth International Conference on Learning Representations (ICLR), 2025.
- Zijian Li*, Yifan Shen*, Kaitao Zheng, Ruichu Cai, Xiangchen Song, Mingming Gong, Guangyi Chen, Kun Zhang, On the Identification of Temporal Causal Representation with Instantaneous Dependence, The Thirteenth International Conference on Learning Representations (ICLR), 2025, Oral.
- Zijian Li*, Shunxing Fan*, Yujia Zheng, Ignavier Ng, Shaoan Xie, Guangyi Chen, Xinshuai Dong, Ruichu Cai, Kun Zhang, Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning, The Thirteenth International Conference on Learning Representations (ICLR), 2025.
- Yuke Li*, Yujia Zheng*, Guangyi Chen, Kun Zhang, Heng Huang, Identification of Intermittent Temporal Latent Process, The Thirteenth International Conference on Learning Representations (ICLR), 2025.
- Ruichu Cai, Zhifan Jiang, Kaitao Zheng, Zijian Li, Weilin Chen, Xuexin Chen, Yifan Shen, Guangyi Chen, Zhifeng Hao, Kun Zhang, Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals, Proceedings of the ACM Web Conference (WWW), 2025.
- Lingjing Kong*, Guangyi Chen*, Petar Stojanov, Haoxuan Li, Eric P. Xing, Kun Zhang, Towards Understanding Extrapolation: a Causal Lens, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2024. [Code]
- Lingjing Kong, Guangyi Chen, Biwei Huang, Eric P. Xing, Yuejie Chi, Kun Zhang, Learning Discrete Concepts in Latent Hierarchical Models , Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2024.
- Xiangchen Song, Zijian Li, Guangyi Chen, Yujia Zheng, Yewen Fan, Xinshuai Dong, Kun Zhang, Causal Temporal Representation Learning with Nonstationary Sparse Transition, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2024.
- Loka Li, Haoyue Dai, Hanin Al Ghothani, Biwei Huang, Jiji Zhang, Shahar Harel, Isaac Bentwich, Guangyi Chen, Kun Zhang, On Causal Discovery in the Presence of Deterministic Relations, Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS), 2024. [Code]
- Hanqi Yan, Yanzheng Xiang, Guangyi Chen, Yifei Wang, Lin Gui, Yulan He, Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective, The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. [Code]
- Zuyan Liu, Benlin Liu, Jiahui Wang, Yuhao Dong, Guangyi Chen, Yongming Rao, Ranjay Krishna, Jiwen Lu, Efficient inference of vision instruction-following models with elastic cache, Proceedings of the European Conference on Computer Vision (ECCV), 2024 [Code]
- Guangyi Chen*, Yifan Shen*, Zhenhao Chen*, Xiangchen Song, Yuewen Sun, Weiran Yao, Xiao Liu, Kun Zhang, CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process, International Conference on Machine Learning (ICML), 2024. [Code]
- Yuke Li*, Guangyi Chen*, Ben Abramowitz, Stefano Anzellott, Donglai Wei, Learning Domain-Invariant Causal Temporal Dynamics for Few-Shot Action Recognition, International Conference on Machine Learning (ICML), 2024.
- Shiyi Zhang, Sule Bai, Guangyi Chen, Lei Chen, Jiwen Lu, Junle Wang, Yansong Tang, Narrative Action Evaluation with Prompt-Guided Multimodal Interaction, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [Code]
- Guangyi Chen*, Yuke Li*, Xiao Liu, Zijian Li, Eman Al Suradi, Donglai Wei, Kun Zhang, LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer, The Twelfth International Conference on Learning Representations (ICLR), 2024. [Code]
- Songyao Jin, Feng Xie, Guangyi Chen, Biwei Huang, Zhengming Chen, Xinshuai Dong, Kun Zhang, Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability, The Twelfth International Conference on Learning Representations (ICLR), 2024. [Code]
- Longkang Li, Ignavier Ng, Gongxu Luo, Biwei Huang, Guangyi Chen, Tongliang Liu, Bin Gu, Kun Zhang, Federated Causal Discovery from Heterogeneous Data, The Twelfth International Conference on Learning Representations (ICLR), 2024. [Code]
- Sheng Zhang, Muzammal Naseer, Guangyi Chen, Zhiqiang Shen, Salman Khan, Kun Zhang, Fahad Khan, Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment , Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024, Oral. [Code]
- Zijian Li, Ruichu Cai, Guangyi Chen, Boyang Sun, Zhifeng Hao, Kun Zhang, Subspace Identification for Multi-Source Domain Adaptation, Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023, Spotlight. [Code]
- Xiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong, Guangyi Chen, Juan Carlos Niebles, Eric Xing, Kun Zhang, Temporally Disentangled Representation Learning under Unknown Nonstationarity, Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.
- Rongqing Li, Changsheng Li, Dongchun Ren, Guangyi Chen, Ye Yuan, Guoren Wang, BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction, Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.
- Guangyi Chen*, XiaoLiu*, Guangrun Wang, Kun Zhang, Philip H.S. Torr, Xiao-Ping Zhang, Yansong Tang, Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer, IEEE International Conference on Computer Vision (ICCV), 2023. [Code]
- Jiaqi Sun, Lin Zhang, Guangyi Chen, Kun Zhang, Peng XU, Yujiu Yang, Feature Expansion for Graph Neural Networks, International Conference on Machine Learning (ICML), 2023. [Code]
- Guangyi Chen*, Zhenhao Chen*, Shunxing Fan, Kun Zhang, Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [Code]
- Lingjing Kong*, Martin Q. Ma*, Guangyi Chen, Eric P. Xing, Yuejie Chi, Louis-Philippe Morency, Kun Zhang, Understanding Masked Autoencoders via Hierarchical Latent Variable Models, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Highlight.
- Tianjun Yao, Jiaqi Sun, Defu Cao, Kun Zhang, Guangyi Chen, MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification, Proceedings of the ACM Web Conference (WWW), 2024.
- Sheng Zhang, Salman Khan, Zhiqiang Shen, Muzammal Naseer, Guangyi Chen, Fahad Khan, PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [Code]
- Guangyi Chen, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, Kun Zhang, PLOT: Prompt Learning with Optimal Transport for Vision-Language Models, The Eleventh International Conference on Learning Representations (ICLR), 2023, Spotlight. [Code]
- Junlong Li*, Guangyi Chen, Yansong Tang, Jinan Bao, Kun Zhang, Jie Zhou, Jiwen Lu, GAIN: On the Generalization of Instructional Action Understanding, The Eleventh International Conference on Learning Representations (ICLR), 2023. [Dataset] [Code]
- Qiaosong Chu, Shuyan Li, Guangyi Chen, Kai Li, Xiu Li, Adversarial Alignment for Source Free Object Detection, Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023, Oral. [Code]
- Weiran Yao, Guangyi Chen, Kun Zhang, Temporally Disentangled Representation Learning, Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022. [Code]
- Lingjing Kong, Shaoan Xie, Weiran Yao, Yujia Zheng, Guangyi Chen, Petar Stojanov, Victor Akinwande, Kun Zhang, Partial disentanglement for domain adaptation, International Conference on Machine Learning (ICML), 2022. [Code]
- Tianpei Gu*, Guangyi Chen*, Junlong Li, Chunze Lin, Yongming Rao, Jie Zhou, and Jiwen Lu, Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Code]
- Yongming Rao, Wenliang Zhao, Guangyi Chen, Yansong Tang, Zheng Zhu, Guan Huang, Jie Zhou, and Jiwen Lu, DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Code] [Project]
- Jinglin Xu*, Yongming Rao*, Xumin Yu, Guangyi Chen, Jie Zhou, and Jiwen Lu, FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, Oral. [Code] [Project]
- Jinglin Xu*, Guangyi Chen*, Jiwen Lu, and Jie Zhou, Unintentional Action Localization via Counterfactual Examples, IEEE Transactions on Image Processing (TIP), 2022
- Jinglin Xu*, Guangyi Chen*, Jiwen Lu, and Jie Zhou, Probabilistic Temporal Modeling for Unintentional Action Localization, IEEE Transactions on Image Processing (TIP), 2022
- Guangyi Chen, Junlong Li, Jiwen Lu, and Jie Zhou, Human Trajectory Prediction via Counterfactual Analysis, IEEE International Conference on Computer Vision (ICCV), 2021 [Code]
- Guangyi Chen, Junlong Li, Nuoxing Zhou, Liangliang Ren, and Jiwen Lu, Personalized Trajectory Prediction via Distribution Discrimination, IEEE International Conference on Computer Vision (ICCV), 2021 [Code]
- Yongming Rao*, Guangyi Chen*, Jiwen Lu and Jie Zhou, Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification, IEEE International Conference on Computer Vision (ICCV), 2021 [Code]
- Guangyi Chen, Tianpei Gu, Jiwen Lu, Jin-An Bao, and Jie Zhou, Person Re-identification via Attention Pyramid, IEEE Transactions on Image Processing (TIP), 2021 [Code]
- Guangyi Chen*, Yongming Rao*, Jiwen Lu and Jie Zhou, Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?, Proceedings of the European Conference on Computer Vision (ECCV), 2020
- Guangyi Chen, Yuhao Lu, Jiwen Lu and Jie Zhou, Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification, Proceedings of the European Conference on Computer Vision (ECCV), 2020
- Guangyi Chen, Jiwen Lu, Ming Yang, and Jie Zhou, Learning Recurrent 3D Attention for Video-Based Person Re-identification, IEEE Transactions on Image Processing (TIP), 2020
- Guangyi Chen, Tianren Zhang, Jiwen Lu and Jie Zhou, Deep Meta Metric Learning, IEEE International Conference on Computer Vision (ICCV), 2019 [Code]
- Guangyi Chen, Chunze Lin, Liangliang Ren, Jiwen Lu and Jie Zhou Self-Critical Attention Learning for Person Re-Identification, IEEE International Conference on Computer Vision (ICCV), 2019
- Guangyi Chen, Jiwen Lu, Ming Yang, and Jie Zhou, Spatial-Temporal Attention-aware Learning for Video-based Person Re-identification, IEEE Transactions on Image Processing (TIP), 2019
Honors and Awards
Teaching
Academic Services