Publications

1. 2026

   Towards Human-Centered Safety in Vision-Language-Action Robot Control: A Survey and Outlook

   Surveys how safety-relevant understanding shapes robot actions across design, deployment, and validation.

   Nhat Chung*, Toan Nguyen*, Tianrun Hu, Yun Xing, Puming Jiang, Tuan-Anh Vu, Bohao Qu, Yedi Zhang, Yue Cao, Jie Zhang, Qing Guo, Yue Wang, Ming-Ming Cheng, Jin Song Dong, Cheston Tan, Harold Soh, David Hsu, Daniel Seita, Ivor Tsang

   Preprints.org Preprint, 2026

   Paper
2. 
   2026

   Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion

   Extends camouflaged instance segmentation to categories unseen in training.

   Tuan-Anh Vu, Duc Thanh Nguyen, Qing Guo, Nhat Chung, Binh-Son Hua, Ivor W. Tsang, Sai-Kit Yeung

   International Journal of Computer Vision (IJCV), 2026

   Paper arXiv
3. 
   2026

   MAGIC: Mastering Physical Adversarial Generation in Context Through Collaborative LLM Agents

   Exposes physical vulnerabilities in driving detectors with scene-aware adversarial patches.

   Yun Xing, Nhat Chung, Jie Zhang, Yue Cao, Ivor Tsang, Yang Liu, Lei Ma, Qing Guo

   AAAI 2026

   Paper arXiv
4. 
   2026

   Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective

   Benchmarks robot memory when manipulation depends on earlier object interactions.

   Nhat Chung*, Taisei Hanyu*, Toan Nguyen, Huy Le, Frederick Bumgarner, Duy Minh Ho Nguyen, Khoa Vo, Kashu Yamazaki, Chase Rainwater, Tung Kieu, Anh Nguyen, Ngan Le

   AAAI 2026

   Paper arXiv Project Code Models
5. 
   2026

   SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation

   Uses fewer visual tokens while retaining competitive manipulation performance.

   Taisei Hanyu*, Nhat Chung*, Huy Le, Toan Nguyen, Yuki Ikebe, Anthony Gunderman, Duy Minh Ho Nguyen, Khoa Vo, Tung Kieu, Kashu Yamazaki, Chase Rainwater, Anh Nguyen, Ngan Le

   ICRA 2026

   arXiv Project Code Models
6. 
   2026

   UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning

   Handles box- and pixel-level video scene graphs in one efficient model.

   Huy Le, Nhat Chung, Tung Kieu, Jingkang Yang, Ngan Le

   WACV 2026

   Paper arXiv Code
7. 
   2025

   Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding

   Improves robot manipulation amid clutter, missing targets, and background changes.

   Khoa Vo, Taisei Hanyu, Yuki Ikebe, Trong Thang Pham, Nhat Chung, Minh Nhat Vu, Duy Nguyen Ho Minh, Anh Nguyen, Anthony Gunderman, Chase Rainwater, Ngan Le

   arXiv Preprint, 2025

   arXiv Project Code
8. 
   2025

   DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

   Exposes real-world stereo depth failures, including on commercial cameras.

   Yun Xing, Yue Cao, Nhat Chung, Jie M. Zhang, Ivor Tsang, Ming-Ming Cheng, Yang Liu, Lei Ma, Qing Guo

   NeurIPS 2025

   Paper arXiv Code
9. 
   2025

   BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance

   Improves video search despite visual and language bias.

   Huy Le, Nhat Chung, Tung Kieu, Anh Nguyen, Ngan Le

   ACM MM 2025

   Paper arXiv Code
10. 
    2024

    Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography

    Reveals transferable roadside-text attacks against driving vision-language models.

    Nhat Chung, Sensen Gao, Tuan-Anh Vu, Jie Zhang, Aishan Liu, Yun Lin, Jin Song Dong, Qing Guo

    arXiv Preprint, 2024

    arXiv PDF
11. 
    2024

    BgSubNet: Robust Semi-Supervised Background Subtraction in Realistic Scenes

    Enables background subtraction in unseen scenes with less labeled data.

    Nhat Minh Chung, Synh Viet-Uyen Ha

    IEEE Sensors Journal, 2024

    Paper
12. 
    2023

    Tracked-Vehicle Retrieval by Natural Language Descriptions With Multi-Contextual Adaptive Knowledge

    Improves natural-language vehicle retrieval across varied cameras and scenes.

    Huy Le, Quang Qui-Vinh Nguyen, Duc Trung Luu, Truc Chau, Nhat Chung, Synh Ha

    CVPR Workshop 2023 - AI City Challenge Track 2 Winner

    Paper PDF Code
13. 
    2023

    Multi-camera People Tracking With Mixture of Realistic and Synthetic Knowledge

    Tracks people across real cameras after training only on synthetic data.

    Quang Qui-Vinh Nguyen, Huy Le, Truc Chau, Duc Trung Luu, Nhat Chung, Synh Ha

    CVPR Workshop 2023 - AI City Challenge Track 1 Runner-up

    Paper PDF Code
14. 
    2022

    Multi-Camera Multi-Vehicle Tracking with Domain Generalization and Contextual Constraints

    Tracks similar vehicles across cameras despite scarce labeled data.

    Nhat Chung, Huy Le, Vuong Nguyen, Quang Qui-Vinh Nguyen, Thong Nguyen, Tin Thai, Synh Ha

    CVPR Workshop 2022

    Paper
15. 
    2022

    Tracked-vehicle Retrieval by Natural Language Descriptions with Domain Adaptive Knowledge

    Adapts vehicle search to unseen scenarios with less data and compute.

    Huy Le*, Quang Qui-Vinh Nguyen*, Vuong Nguyen, Thong Nguyen, Nhat Chung, Tin Thai, Synh Ha

    CVPR Workshop 2022

    Paper PDF
16. 
    2021

    Tiny-PIRATE: A Tiny Model With Parallelized Intelligence for Real-Time Analysis as a Traffic countEr

    Enables real-time vehicle counting on resource-limited edge devices.

    Synh Ha, Nhat Chung, Tien-Cuong Nguyen, Hung Ngoc Phan

    CVPR Workshop 2021 - AI City Challenge Track 1 Runner-up

    Paper PDF

* denotes equal contribution.