Portfolio

_

I'm a PhD student at MBZUAI focusing on computer vision, where I work on video reasoning and interactive world models under the supervision of Prof. Fahad Khan. I am currently a research intern at the Institute of Foundation Models (IFM), focusing on memory for world models. From my early days tinkering with computers, I've been passionate about how technology can transform human ideas into reality—particularly in creating visuals that help share stories, dreams, and experiences. In my free time, I love traveling, gaming, indulging in good food, watching anime, and diving into philosophical discussions.

Latest News

• 2026.07: Started a research internship at the Institute of Foundation Models (IFM), focusing on memory for world models.
• 2024.10: 🎉 Received grant funding for travel trip to ECAI and ACCV.
• 2024.09: 🎉 Received Reginald R. ‘Barney’ & Jameson A. Baxter Graduate Fellowship.

Publications

1. Counting to Four is still a Chore for VLMs
   Duy Le Dinh Anh, Patrick Amadeus Irawan, Tuan Van Vo — CVPRW 2026, 5th Workshop on Multimodal Foundation Models (MMFM)
2. Enhanced Kalman with Adaptive Appearance Motion SORT for Grounded Generic Multiple Object Tracking
   Duy Le Dinh Anh, Kim Hoang Tran, Quang-Thuc Nguyen, Ngan Hoang Le — ACCV 2024 (oral)
3. TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORT
   Duy Le Dinh Anh, Kim Hoang Tran, Ngan Hoang Le — ECAI 2024 (oral)
4. ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
   Thinh Phan, Khoa Vo, Duy Le, Gianfranco Doretto, Donald Adjeroh, Ngan Le — WACV 2024
5. Z-GMOT: Zero-shot Generic Multiple Object Tracking
   Kim Hoang Tran, Anh Duy Le Dinh, Tien Phat Nguyen, Thinh Phan, Pha Nguyen, Khoa Luu, Donald Adjeroh, Gianfranco Doretto, Ngan Hoang Le — NAACL Findings 2024
6. AANet: Motorcycle ReID Using Multi-Atrous Convolution and Self-Attention Mechanisms
   Trong-Hieu Nguyen-Mau, Kim-Trang Phu-Thi, Anh-Duy Le-Dinh, Minh-Triet Tran, Hai-Dang Nguyen — MAPR 2023

Education & Careers

• [2026 – Present] Institute of Foundation Models (IFM): Research Intern, Memory for World Models
• [2025 – Present] MBZUAI: PhD Student
• [2024 – 2025] University of Arkansas: Research Assistant
• [2023 – 2024] FPT Software — AI Center: Residency
• [2020 – 2023] Phenikaa MaaS: AI Team Lead / Backend Engineer
• [2019 – 2020] HCMUS — Computational Linguistic Center: Research Student
• [2018 – 2019] Piksal Studio: Backend Engineer
• [2017 – 2022] University of Science (HCMUS): Bachelor
• [2014 – 2017] Le Hong Phong High School for the Gifted

Visitors

Total visits: