@inproceedings{zha2026physiology,title={Physiology as Language: Translating Respiration to EEG during Sleep},author={Zha*, Kaiwen and Li*, Chao and He*, Hao and Cao, Peng and Li, Tianhong and Mirzazadeh, Ali and Zhang, Ellen and Lee, Jong Woo and Kim, Yoon and Katabi, Dina},note={*Co-first authors},booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)},year={2026},eprint={2602.00526},}
@inproceedings{li2026unifying,title={Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation},author={Li, Chao and Li, Tianhong and Nuthalapati, Sai Vidyaranya and Chen, Hong-You and Shukla, Satya Narayan and Cheng, Jianpeng and Yang, Yonghuan and Xiao, Jun and Fan, Xiangjun and Singh, Aashu and Katabi, Dina and Mishra, Shlok Kumar},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2026},eprint={2603.02667},}
2025
Adv. Funct. Mater.
Zero Field Antiferromagnetically Coupled Skyrmions and their Field-Driven Uncoupling in Composite Chiral Multilayers
May Inn Sim, Dickson Thian, Ramu Maddu, and
5 more authors
@article{mayinnsim,title={Zero Field Antiferromagnetically Coupled Skyrmions and their Field-Driven Uncoupling in Composite Chiral Multilayers},author={Sim, May Inn and Thian, Dickson and Maddu, Ramu and Chen, Xiaoye and Tan, Hang Khume and Li, Chao and Ho, Pin and Soumyanarayanan, Anjan},journal={Advanced Functional Materials},volume={35},pages={2416927},year={2025},doi={10.1002/adfm.202416927},url={https://doi.org/10.1002/adfm.202416927},dimensions={true}}
Uncovering Sleep and Respiratory Biomarkers in Rett Syndrome via Passive At-Home Monitoring
Chao Li, Rumen Hristov, Michail Ouroutzoglou, and
11 more authors
@inproceedings{rett,title={Uncovering Sleep and Respiratory Biomarkers in Rett Syndrome via Passive At-Home Monitoring},author={Li, Chao and Hristov, Rumen and Ouroutzoglou, Michail and Krishna, Pranav and Levy, Rachel and Mirzazadeh, Ali and DeBisschop, Curtis and Coughlin, Michelle and Von Hehn, Jana and Coenraads, Monica and Rahul, Hariharan and Carpenter, Randall and Lieberman, David and Katabi, Dina},booktitle={Rett Syndrome Scientific Meeting},year={2025},month=jun}
2024
What radio waves tell us about sleep!
Hao He*, Chao Li*, Wolfgang Ganglberger, and
7 more authors
@article{10.1093/sleep/zsae187,title={What radio waves tell us about sleep!},author={He*, Hao and Li*, Chao and Ganglberger, Wolfgang and Gallagher, Kaileigh and Hristov, Rumen and Ouroutzoglou, Michail and Sun, Haoqi and Sun, Jimeng and Westover, M Brandon and Katabi, Dina},note={*Co-first authors},journal={Sleep},pages={zsae187},year={2024},month=aug,issn={0161-8105},doi={10.1093/sleep/zsae187},url={https://doi.org/10.1093/sleep/zsae187},dimensions={true}}
WiOpt
Achieving AoI Fairness in Spatially Distributed Wireless Networks: From Theory to Implementation
Nicholas Jones, Joshua Wornell, Chao Li, and
1 more author
In 22nd International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt 2024), Aug 2024
@inproceedings{jones2024achieving,title={Achieving AoI Fairness in Spatially Distributed Wireless Networks: From Theory to Implementation},author={Jones, Nicholas and Wornell, Joshua and Li, Chao and Modiano, Eytan},booktitle={22nd International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt 2024)},year={2024},dimensions={true}}
2022
SoftTouch: A Sensor-Placement Framework for Soft Robotic Hands
Chao Li, and Nancy Pollard
In 2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids), Aug 2022
@inproceedings{10000138,title={SoftTouch: A Sensor-Placement Framework for Soft Robotic Hands},author={Li, Chao and Pollard, Nancy},booktitle={2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)},volume={},number={},pages={504-511},year={2022},doi={10.1109/Humanoids53995.2022.10000138},dimensions={true}}
Exploring mmWave Radar and Camera Fusion for High-Resolution and Long-Range Depth Imaging
Akarsh Prabhakara, Diana Zhang, Chao Li, and
4 more authors
In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Aug 2022
@inproceedings{9982080,title={Exploring mmWave Radar and Camera Fusion for High-Resolution and Long-Range Depth Imaging},author={Prabhakara, Akarsh and Zhang, Diana and Li, Chao and Munir, Sirajum and Sankaranarayanan, Aswin C. and Rowe, Anthony and Kumar, Swarun},booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},volume={},number={},pages={3995-4002},year={2022},doi={10.1109/iros47612.2022.9982080},dimensions={true}}
2021
The Elliott and Connolly Benchmark: A Test for Evaluating the In-Hand Dexterity of Robot Hands
Ryan Coulson, Chao Li, Carmel Majidi, and
1 more author
In 2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids), Aug 2021
@inproceedings{9555798,title={The Elliott and Connolly Benchmark: A Test for Evaluating the In-Hand Dexterity of Robot Hands},author={Coulson, Ryan and Li, Chao and Majidi, Carmel and Pollard, Nancy S.},booktitle={2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)},volume={},number={},pages={238-245},year={2021},doi={10.1109/HUMANOIDS47582.2021.9555798},}
Semi-supervised classification of radiology images with NoTeacher: A teacher that is not mean
Balagopal Unnikrishnan, Cuong Nguyen, Shafa Balaram, and
3 more authors
Deep learning models achieve strong performance for radiology image classification, but their practical application is bottlenecked by the need for large labeled training datasets. Semi-supervised learning (SSL) approaches leverage small labeled datasets alongside larger unlabeled datasets and offer potential for reducing labeling cost. In this work, we introduce NoTeacher, a novel consistency-based SSL framework which incorporates probabilistic graphical models. Unlike Mean Teacher which maintains a teacher network updated via a temporal ensemble, NoTeacher employs two independent networks, thereby eliminating the need for a teacher network. We demonstrate how NoTeacher can be customized to handle a range of challenges in radiology image classification. Specifically, we describe adaptations for scenarios with 2D and 3D inputs, with uni and multi-label classification, and with class distribution mismatch between labeled and unlabeled portions of the training data. In realistic empirical evaluations on three public benchmark datasets spanning the workhorse modalities of radiology (X-Ray, CT, MRI), we show that NoTeacher achieves over 90-95% of the fully supervised AUROC with less than 5–15% labeling budget. Further, NoTeacher outperforms established SSL methods with minimal hyperparameter tuning, and has implications as a principled and practical option for semi-supervised learning in radiology applications.
@article{UNNIKRISHNAN2021102148,title={Semi-supervised classification of radiology images with NoTeacher: A teacher that is not mean},author={Unnikrishnan, Balagopal and Nguyen, Cuong and Balaram, Shafa and Li, Chao and Foo, Chuan Sheng and Krishnaswamy, Pavitra},journal={Medical Image Analysis},volume={73},pages={102148},year={2021},issn={1361-8415},doi={10.1016/j.media.2021.102148},url={https://www.sciencedirect.com/science/article/pii/S1361841521001948},keywords={Semi-supervised deep learning, Classification, Radiographs, MRI, Mean teacher, Co-training},dimensions={true}}
