Xin Chen

My research spans the areas of machine learning (ML)/deep learning (DL), computer vision, efficient AI, ML system, LLMs. I focus on training/fine-tuning large DL models, building large-scale GPU clusters, optimizing models for deployment, and developing learning algorithms and theory. These research themes provide a solid foundation for reaching my long-term objective: making AI systems efficient and scalable.
Currently, I am Machine Learning Software Engineer at Intel. Before joining Intel, I gained experience working with various academic institutions and industry R&D teams.

Email / CV / Google Scholar / Github

News

[7/2024] One paper about defending unlearning diffusion models with adversarial training for robust concept erasure was accepted to NIPS 2024.
[9/2024] One paper about evaluating unlearned diffusion models was accepted to ECCV 2024.
[6/2024] Will Serve as Moderator of Innovation Forums of IEEE MIPR 2024, Industry Challenges of Efficient AI[Link].
[5/2024] One paper about CoT distillation of LLMs was accepted to ACL Findings 2024.
[4/2024] One paper about efficient DNN deployment was accepted to ICS'24.
[2/2023] One paper about joint text and visual prompt tuning to boost 2D CNN model perforamce in temporal video grounding was accepted to CVPR2023.

Selected Publications [Google Scholar]

(*Equal Contribution, ^†Corresponding Author)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding and Sijia Liu
The 38th Annual Conference on Neural Information Processing Systems (NIPS), 2024 [Paper] [Code]
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images... For Now
Yimeng Zhang*, Jinghan Jia*, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, Sijia Liu
European Conference on Computer Vision (ECCV), 2024 [Paper] [Project] [Code] [HF Benchmark]
Learning to Maximize Mutual Information for Chain-of-Thought Distillation
Xin Chen, Hanxian Huang, Yanjun Gao, Yi Wang, Jishen Zhao, Ke Ding
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2024 [Paper] [Code]
Fasor: A Fast Tensor Program Optimization Framework for Efficient DNN Deployment
Hanxian Huang, Xin Chen, Jishen Zhao
Proceedings of the 38th ACM International Conference on Supercomputing (ICS), 2024 [Paper]
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation
Linfeng Zhang, Xin Chen, Runpei Dong, Kaisheng Ma
British Machine Vision Conference (BMVC), 2023 [Paper] [Code]
Influence of Data Distribution on Federated Learning Performance in Tumor Segmentation
Guibo Luo,Tianyu Liu, Jinghui Lu,Xin Chen, Lequan Yu, Jian Wu, Danny Z. Chen, Wenli Cai
Radiology: Artificial Intelligence, April 2023 [Paper]
Text-Visual Prompting for Efficient 2D Temporal Video Grounding
Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [Paper] [Project] [Code] [HF Model]
Contrastive Deep Supervision
Linfeng Zhang, Xin Chen, Junbo Zhang, Runpei Dong, Kaisheng Ma
European Conference on Computer Vision (ECCV), 2022 (Oral, 2.7% acceptance ratio) [Paper] [Code]
Pruning-as-Search: Efficient Neural Architecture Search via Automatic Channel Pruning and Structural Reparameterization
Yanyu Li, Pu Zhao, Geng Yuan, Xue Lin, Yanzhi Wang, Xin Chen^†
31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI), 2022 [Paper] [Code]
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation
Linfeng Zhang, Xin Chen, Xiaobing Tu, Pengfei Wan, Ning Xu, Kaisheng Ma
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 [Paper] [Code]
Attention Distillation for Learning Video Representations
Miao Liu, Xin Chen, Yun Zhang, Yin Li, James M Rehg
British Machine Vision Conference (BMVC), 2020 (Oral, 5% acceptance ratio) [Paper] [Project]
Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation
Heyi Liu, Yuke Tian, Klaus Mueller, Xin Chen^†
Image and Vision Computing, Volume 83, March, 2019 [Paper] [Code]
Fully-coupled two-stream spatiotemporal networks for extremely low resolution action recognition
Mingze Xu, Aidean Sharghi, Xin Chen^†, David J Crandall
IEEE Winter Conference on Applications of Computer Vision (WACV), 2018 [Paper] [Code]
Motion Saliency Based Automatic Delineation of Glottis Contour in High-speed Digital Images
Xin Chen, Emma Marriott, Yuling Yan
IEEE Conference on Industrial Electronics and Applications ((ICIEA)), 2017 [Paper]
Parallel nonparametric binarization for degraded document images
Xin Chen, Liang Lin, Yuefang Gao
Neurocomputing, Volume 189, 2016 [Paper]
Large-scale support vector machine classification with redundant data reduction
Xiang-Jun Shen, Lei Mu, Zhen Li, Hao-Xiang Wu, Jian-Ping Gou, Xin Chen
Neurocomputing, Volume 172, 2016
CUDA-accelerated fast Sauvola’s method on Kepler architecture
Xin Chen, Yuefang Gao, Zhonghong Huang
Multimedia Tools and Applications, Volume 74, 2015 [Paper]
Saliency Mapping Enhanced by Structure Tensor
Zhiyong He, Xin Chen, Lining Sun
Computational Intelligence and Neuroscience, 2015 [Paper]
Automatic tracing of vocal-fold motion from high-speed digital images
Yuling Yan, Xin Chen, Diane Bless
IEEE Transactions on Biomedical Engineering, Volume 53, Issue 7, 2006 [Paper]
A segmentation scheme based on Rayleigh distribution model for extracting glottal waveform from high-speed laryngeal images
Xin Chen, Diane Bless, Yuling Yan
IEEE Engineering in Medicine and Biology 27th Annual Conference (EMBS), 2005
Biomedical image analysis in high-speed laryngeal imaging of voice production
Yuling Yan, Diane Bless, Xin Chen
IEEE Engineering in Medicine and Biology 27th Annual Conference (EMBS), 2005

Granted Patents

Multi-level intermediate representation decoder for heterogeneous platforms
Zhen Peng, Yang Liu, Hanxian Huang, Yongxiong Ren, YANG Jishen, Lingzhi Liu, Xin Chen, US11928446B2, 3/2024.
Method and system for providing air conditioning
Xin Chen, Zhicai Ou, Hua Zhou, Rubao Mao, US20210356161A1, 5/2022.
Personalized Laundry Appliance
Xin Chen, Hua Zhou, Yu Zhu, Yuxiang Gao, US10563338B2, 2/2020.
Face Recognition in a Residential Environment.
Dongyan Wang, Xin Chen, Hua Zhou, US10650273B2, 5/2019.

Honors & Awards

Division Achievement Award for Medical Image Segmentation project, Q3 2022, AIA Group of Intel
Rank #4 (out of 93) in Task 1 of Multi-Modality Abdominal Multi-Organ Segmentation Challenge 2022 (MICCAI2022)
Rank #2 in track 2 and rank #3 in track 3 at 2018 Low-Power Image Recognition Challenge (LPIRC 2018 with CVPR) (Manager of the team)
2005 University of Hawaii Graduate International Traveling Award

Professional Activities

Conference Reviews:
AAAI 2022, 2023, 2024, 2025
CVPR 2022, 2023,2024
ECCV 2022, 2024
ICCV 2023
WACV 2023, 2024
Journal Reviews:
IEEE Transactions on Neural Networks and Learning Systems
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Multimedia
Medical Image Analysis