TL;DR: Long videos contain a lot of redundancy. Instead of processing everything uniformly, we treat the VLM as an active sensor and use Bayesian active search to decide where to look next — allocating the visual budget to the most informative moments.
@inproceedings{tang2026vlm,title={The VLM as Sensor: Bayesian Active Search for Long Video Understanding},author={Tang, Chong and Ek, S. and Koch, D. and Mullins, R. D. and Weddell, A. S. and Chauhan, J.},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2026},}
NeurIPS
MOSAIC: Concept Bottlenecks via Text-Anchored Optimal Transport
S. Ek, Chong Tang, D. Koch, A. S. Weddell, J. Chauhan, and R. D. Mullins
In Advances in Neural Information Processing Systems (NeurIPS), 2026
TL;DR: We rethink concept bottleneck models through text-anchored optimal transport, building a more structured connection between visual evidence and human-readable concepts rather than relying only on global embedding similarity.
@inproceedings{ek2026mosaic,title={MOSAIC: Concept Bottlenecks via Text-Anchored Optimal Transport},author={Ek, S. and Tang, Chong and Koch, D. and Weddell, A. S. and Chauhan, J. and Mullins, R. D.},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2026}}
NeurIPS
SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language Grounding
S. Ek, Chong Tang, D. Koch, A. S. Weddell, J. Chauhan, and R. D. Mullins
In Advances in Neural Information Processing Systems (NeurIPS), 2026
TL;DR: We decouple multispectral representation learning from vision-language grounding, allowing rich spectral knowledge to be learned while maintaining flexible alignment with language for Earth-observation tasks.
@inproceedings{ek2026spext,title={SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language Grounding},author={Ek, S. and Tang, Chong and Koch, D. and Weddell, A. S. and Chauhan, J. and Mullins, R. D.},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2026}}
NeurIPS
Test-Time Graph Anomaly Detection via Shifted Augmentation with Dynamic Objective Scheduling
C. Xiao, R. Fan, T. Zhao, F. Zhou, Chong Tang, and Y. Ma
In Advances in Neural Information Processing Systems (NeurIPS), 2026
TL;DR: We tackle distribution shifts in graph anomaly detection at deployment time through shifted augmentation + dynamically scheduled adaptation objectives, helping the detector adjust when test-time graphs differ from training data.
@inproceedings{xiao2026testtime,title={Test-Time Graph Anomaly Detection via Shifted Augmentation with Dynamic Objective Scheduling},author={Xiao, C. and Fan, R. and Zhao, T. and Zhou, F. and Tang, Chong and Ma, Y.},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2026}}
NeurIPS
Structure-Semantic Guided Closed-Loop Medical Anomaly Detection via Multi-Agent Collaboration
C. Xiao, Y. Dai, Y. Fu, Y. Wang, Chong Tang, F. Zhou, and Y. Ma
In Advances in Neural Information Processing Systems (NeurIPS), 2026
TL;DR: We combine structural and semantic evidence with a closed-loop multi-agent framework, where specialized agents collaborate to iteratively detect, verify, and refine medical anomaly decisions.
@inproceedings{xiao2026structure,title={Structure-Semantic Guided Closed-Loop Medical Anomaly Detection via Multi-Agent Collaboration},author={Xiao, C. and Dai, Y. and Fu, Y. and Wang, Y. and Tang, Chong and Zhou, F. and Ma, Y.},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2026}}
ICLR
SURGE: Surprise-Guided Token Reduction for Efficient Video Understanding with VLMs
Chong Tang, S. Ek, D. Koch, R. D. Mullins, A. S. Weddell, and J. Chauhan
In International Conference on Learning Representations (ICLR), 2026
@inproceedings{tang2026surge,title={SURGE: Surprise-Guided Token Reduction for Efficient Video Understanding with VLMs},author={Tang, Chong and Ek, S. and Koch, D. and Mullins, R. D. and Weddell, A. S. and Chauhan, J.},booktitle={International Conference on Learning Representations (ICLR)},year={2026},}
IEEE IoT-J
Parallax: Runtime Parallelization for Operator Fallbacks in Heterogeneous Edge Systems
@article{tang2026parallax,title={Parallax: Runtime Parallelization for Operator Fallbacks in Heterogeneous Edge Systems},author={Tang, Chong and Dai, H. and Chauhan, J.},journal={IEEE Internet of Things Journal},year={2026}}
EAAI
Hierarchical Mental-States Reasoning with Dynamic Fusion World Models for Imperfect Multi-UAV Cooperative-Competitive Environments
J. Cheng, N. Li, C. Dong, and Chong Tang
Engineering Applications of Artificial Intelligence, 2026
@article{cheng2026hierarchical,title={Hierarchical Mental-States Reasoning with Dynamic Fusion World Models for Imperfect Multi-UAV Cooperative-Competitive Environments},author={Cheng, J. and Li, N. and Dong, C. and Tang, Chong},journal={Engineering Applications of Artificial Intelligence},year={2026}}
2025
NeurIPS
PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth Observation
Chong Tang, J. Powell, D. Koch, R. D. Mullins, A. S. Weddell, and J. Chauhan
In Advances in Neural Information Processing Systems (NeurIPS), 2025
@inproceedings{tang2025physwin,title={PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth Observation},author={Tang, Chong and Powell, J. and Koch, D. and Mullins, R. D. and Weddell, A. S. and Chauhan, J.},booktitle={Advances in Neural Information Processing Systems (NeurIPS)},year={2025},}
IEEE TMC
ML-Track: Passive Human Tracking Using WiFi Multi-Link Round-Trip CSI and Particle Filter
F. Shi, W. Li, Chong Tang, Y. Fang, P. V. Brennan, and K. Chetty
@article{shi2025mltrack,title={ML-Track: Passive Human Tracking Using WiFi Multi-Link Round-Trip CSI and Particle Filter},author={Shi, F. and Li, W. and Tang, Chong and Fang, Y. and Brennan, P. V. and Chetty, K.},journal={IEEE Transactions on Mobile Computing},year={2025}}
KBS
Enhancing Multi-Agent Reinforcement Learning via World Model Assisted Single-Agent Population Policies in Multi-UAV Cooperative-Competitive Scenarios
@article{cheng2025marl,title={Enhancing Multi-Agent Reinforcement Learning via World Model Assisted Single-Agent Population Policies in Multi-UAV Cooperative-Competitive Scenarios},author={Cheng, J. and Li, N. and Dong, C. and Tang, Chong},journal={Knowledge-Based Systems},year={2025}}
2024
EWSN
AdaTM: Logic-Inspired Adaptive Tsetlin Machines for Efficient and Effective Continual Learning on the Edge
Chong Tang, N. Singh, and J. Chauhan
In International Conference on Embedded Wireless Systems and Networks (EWSN), 2024
@inproceedings{tang2024adatm,title={AdaTM: Logic-Inspired Adaptive Tsetlin Machines for Efficient and Effective Continual Learning on the Edge},author={Tang, Chong and Singh, N. and Chauhan, J.},booktitle={International Conference on Embedded Wireless Systems and Networks (EWSN)},year={2024},}
2023
IEEE TAES
MDPose: Human Skeletal Motion Reconstruction Using WiFi Micro-Doppler Signatures
Chong Tang, W. Li, S. Vishwakarma, F. Shi, S. Julier, and K. Chetty
IEEE Transactions on Aerospace and Electronic Systems, 2023
@article{tang2023mdpose,title={MDPose: Human Skeletal Motion Reconstruction Using WiFi Micro-Doppler Signatures},author={Tang, Chong and Li, W. and Vishwakarma, S. and Shi, F. and Julier, S. and Chetty, K.},journal={IEEE Transactions on Aerospace and Electronic Systems},year={2023}}
IEEE JSAC
Decimeter-Level Indoor Localization Using WiFi Round-Trip Phase and Factor Graph Optimization
F. Shi, W. Li, Chong Tang, Y. Fang, P. V. Brennan, and K. Chetty
IEEE Journal on Selected Areas in Communications, 2023
@article{shi2023decimeter,title={Decimeter-Level Indoor Localization Using WiFi Round-Trip Phase and Factor Graph Optimization},author={Shi, F. and Li, W. and Tang, Chong and Fang, Y. and Brennan, P. V. and Chetty, K.},journal={IEEE Journal on Selected Areas in Communications},year={2023}}
2021
IEEE TGRS
FMNet: Latent Feature-Wise Mapping Network for Cleaning Up Noisy Micro-Doppler Spectrogram
Chong Tang, W. Li, S. Vishwakarma, F. Shi, S. J. Julier, and K. Chetty
IEEE Transactions on Geoscience and Remote Sensing, 2021
@article{tang2021fmnet,title={FMNet: Latent Feature-Wise Mapping Network for Cleaning Up Noisy Micro-Doppler Spectrogram},author={Tang, Chong and Li, W. and Vishwakarma, S. and Shi, F. and Julier, S. J. and Chetty, K.},journal={IEEE Transactions on Geoscience and Remote Sensing},year={2021}}
IEEE TWC
On CSI and Passive Wi-Fi Radar for Opportunistic Physical Activity Recognition
W. Li, M. J. Bocus, Chong Tang, R. J. Piechocki, K. Woodbridge, and K. Chetty
IEEE Transactions on Wireless Communications, 2021
@article{li2021csi,title={On CSI and Passive Wi-Fi Radar for Opportunistic Physical Activity Recognition},author={Li, W. and Bocus, M. J. and Tang, Chong and Piechocki, R. J. and Woodbridge, K. and Chetty, K.},journal={IEEE Transactions on Wireless Communications},year={2021}}
2020
IEEE TGRS
Passive WiFi Radar for Human Sensing Using a Stand-Alone Access Point
W. Li, R. J. Piechocki, K. Woodbridge, Chong Tang, and K. Chetty
IEEE Transactions on Geoscience and Remote Sensing, 2020
@article{li2020passive,title={Passive WiFi Radar for Human Sensing Using a Stand-Alone Access Point},author={Li, W. and Piechocki, R. J. and Woodbridge, K. and Tang, Chong and Chetty, K.},journal={IEEE Transactions on Geoscience and Remote Sensing},year={2020}}