I am a researcher working at the intersection of NLP, computer vision, and multimodal learning, with a focus on large multimodal models and video understanding. I received my PhD from the National University of Singapore in September 2025, advised by Professor See-Kiong Ng and Professor Anh-Tuan Luu. My research focuses on building and understanding multimodal models for language, vision, and video.

Specifically, my research program centers on grounding multimodal models in time — building systems that base their predictions on concrete visual evidence in dynamic environments, rather than producing fluent but ungrounded answers. It is organized along three directions:

  1. Building and benchmarking temporal grounding systems. Architectures and benchmarks that force models to recover the temporal evidence supporting their predictions, not just produce plausible final answers. [DemaFormer (EMNLP’23)] [Motion-aware Contrastive (AAAI’25)] [Multi-Scale Contrastive (AAAI’25)] [STEMO (arXiv’26)]

  2. Learning from partial temporal supervision. Treating noisy, incomplete video–text alignment as a core modeling challenge so that models avoid spurious correlations and adapt efficiently under realistic data. [MAMA (ECCV’24)] [READ (AAAI’24)]

  3. Visual foresight. Anticipating future visual states via retrieval-grounded prediction and physics-aware motion-guided animation, rather than free-form generative hallucination. [Eulerian Motion Guidance (arXiv’26)]

My broader vision is to build the temporal infrastructure that makes autonomous multimodal agents trustworthy in dynamic environments — turning temporal grounding from a niche task into a core architectural requirement for reliable multimodal intelligence.

I am open to opportunities for collaboration and new research ideas. If you are interested in working with me, please feel free to contact via my email.

News

Mar 24, 2026 Invited to serve as Area Chair for NeurIPS 2026
Sep 2, 2025 Succesfully defended my PhD thesis: Video Understanding - Through a Temporal Lens
Apr 9, 2025 Invited to serve as Area Chair for NeurIPS 2025.
Dec 10, 2024 Two papers accepted to AAAI 2025.
Oct 25, 2024 Invited to serve as Area Chair for NAACL 2025.
Sep 26, 2024 One paper accepted to NeurIPS 2024.
Sep 20, 2024 One paper accepted to EMNLP 2024.
Jul 2, 2024 One paper accepted to ECCV 2024.
Jun 21, 2024 Invited to serve as Area Chair for EMNLP 2024.
May 16, 2024 Two papers accepted to ACL 2024.
Mar 14, 2024 One paper accepted to NAACL 2024.
Dec 20, 2023 One paper accepted to Artificial Intelligence Review.
Dec 10, 2023 Two papers accepted to AAAI 2024.

Selected Publications

For the full list of my publications: Publications, Google Scholar.

2026

  1. Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency
    Thong Nguyen, Khoi M. Le, Cong-Duy Nguyen, Anh Tuan Luu, See-Kiong Ng, Chunyan Miao
  2. Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models
    Tri Cao, Khoi Le, Thong Nguyen, Cong-Duy Nguyen, Quynh Vo, Anh Tuan Luu, Chunyan Miao, See-Kiong Ng, Shuicheng Yan, Bryan Hooi
  3. WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
    Tri Cao, Yulin Chen, Hieu Cao, Yibo Li, Khoi Le, Thong Nguyen, Yuexin Li, Yufei He, Yue Liu, Shuicheng Yan, Bryan Hooi

2025

  1. Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation
    Thong Nguyen, Xiaobao Wu, Yi Bin, Cong-Duy Nguyen, See-Kiong Ng, Anh Tuan Luu
    In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025)
  2. Multi-Scale Contrastive Learning for Video Temporal Grounding
    Thong Nguyen, Yi Bin, Xiaobao Wu, Zhiyuan Hu, Cong-Duy Nguyen, See-Kiong Ng, Anh Tuan Luu
    In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025)

2024

  1. FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm
    Xiaobao Wu, Thong Nguyen, Delvin Ce Zhang, William Yang Wang, Anh Tuan Luu
    In Advances in Neural Information Processing Systems (NeurIPS 2024)
  2. Encoding and Controlling Global Semantics for Long-form Video Question Answering
    Thong Nguyen, Zhiyuan Hu, Xiaobao Wu, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)
  3. MAMA: A Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
    Thong Nguyen, Yi Bin, Xiaobao Wu, Xinshuai Dong, Zhiyuan Hu, Khoi Le, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
    In Proceedings of the 18th European Conference on Computer Vision (ECCV 2024)
  4. Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
    Thong Nguyen, Yi Bin, Junbin Xiao, Leigang Qu, Yicong Li, Jay Zhangjie Wu, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
    In Proceedings of Findings of 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024 Findings)
  5. KDMCSE: Knowledge distillation multimodal sentence embeddings with adaptive angular margin contrastive learning
    Cong-Duy Nguyen, Thong Nguyen, Xiaobao Wu, Luu Anh Tuan
    In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)
  6. On the affinity, rationality, and diversity of hierarchical topic modeling
    Xiaobao Wu, Fengjun Pan, Thong Nguyen, Yichao Feng, Chaoqun Liu, Cong-Duy Nguyen, Luu Anh Tuan
    In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)
  7. READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
    Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Khoi Le, Zhiyuan Hu, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
    In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)

2023

  1. Improving multimodal sentiment analysis: Supervised angular margin-based contrastive learning for enhanced fusion representation
    Cong-Duy Nguyen, Thong Nguyen, Duc Vu, Luu Anh Tuan
    In Proceedings of Findings of 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 Findings)
  2. Effective Neural Topic Modeling with Embedding Clustering Regularization
    Xiaobao Wu, Xinshuai Dong, Thong Nguyen, Luu Anh Tuan
    In Proceedings of the 40th International Conference on Machine Learning (ICML 2023)
  3. DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
    Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
    In Proceedings of Findings of 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 Findings)
  4. InfoCTM: A Mutual Information Maximization Perspective of Cross-lingual Topic Modeling
    Xiaobao Wu, Xinshuai Dong, Thong Nguyen, Chaoqun Liu, Liangming Pan, Luu Anh Tuan
    In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023)
  5. Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction
    Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Luu Anh Tuan, Cong-Duy Nguyen, Zhen Hai, Lidong Bing
    In Proceedings of Findings of 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023 Findings)

2022

  1. Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions
    Thong Nguyen, Xiaobao Wu, Luu Anh Tuan, Cong-Duy Nguyen, Zhen Hai, Lidong Bing
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)
  2. Improving Neural Cross-Lingual Abstractive Summarization via Employing Optimal Transport Distance for Knowledge Distillation
    Thong Nguyen, Luu Anh Tuan
    In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI 2022)

2021

  1. Contrastive Learning for Neural Topic Model
    Thong Nguyen, Luu Anh Tuan
    In Advances in Neural Information Processing Systems (NeurIPS 2021)
  2. Enriching and Controlling Global Semantics for Text Summarization
    Thong Nguyen, Luu Anh Tuan, Truc Lu, Tho Quan
    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)