Tin Nguyen

Tin (Kevin) Nguyen

🎓 I'm Tin Nguyen, currently pursuing my PhD in Computer Science at Auburn University, working with Anh Totti Nguyen. During this time, I also have the chance to work with Mohammad Reza Taesiri and Chirag Agarwal.
Feel free to reach out via ngthanhtinqn@gmail.com or ttn0011@auburn.edu

Research Intern @ Aikyam Lab, University of Virginia — May–Aug 2026
I'm looking for research internship opportunities around LLMs, VLMs, Agents 👀 Please email me if you think I'd be a good fit — ngthanhtinqn@gmail.com or ttn0011@auburn.edu 🤗

Research Interest

I am particularly interested in making LLMs and VLMs smarter and more controllable via multimodal grounded reasoning, interpretability
Summary about my research [click to expand]

For AI to be a real collaborator, it must:

  • ground its outputs in the user's context — highlighting where the evidence comes from [TMLR'25, Arxiv'26] [see figure ▾]
    HoT figure PageGuide figure
  • explain its reasoning in ways humans can inspect and edit [NAACL'24] [see figure ▾]
    PEEB figure
  • perceive and act in the user's environment through multimodal understanding [KBS'23] [see figure ▾]
    VizDoom figure

Today's large models are impressively general, but often opaque. My research works toward making them transparent, grounded, and collaborative — so that humans can trust, verify, and steer AI in real-world tasks.

Publications my favorites () | others ()

PageGuide paper figure
PageGuide: Browser extension to assist users in navigating a webpage and locating information
Tin Nguyen, Thang T. Truong, Runtao Zhou, Trung Bui, Chirag Agarwal, Anh Totti Nguyen
Arxiv, 2026
Project Page Arxiv Code
HoT paper figure
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Tin Nguyen*, Logan Bolton*, Mohammad Reza Taesiri, Trung Bui, and Anh Totti Nguyen
TMLR, 2026
Also accepted at NeurIPS 2025 Workshop Multimodal Algorithmic Reasoning (MAR) — Oral
Website Code Paper
PEEB paper figure
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
Thang Pham*, Peijie Chen*, Tin Nguyen*, Seunghyun Yoon, Trung Bui, Anh Nguyen
NAACL, 2024 Findings
Code Paper Demo Video
VizDoom navigation figure
Coarse-To-Fine Fusion for Language Grounding in 3D Navigation
Thanh Tin Nguyen*, Anh H. Vo*, Soo-Mi Choi, Yong-Guk Kim
Knowledge-based Systems (KBS), Jul 4, 2023
Video Code Paper
A Very Big Video Reasoning Suite
Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma, Hang He, Yifan Zhou, Lingzi Guo, Lantao Mei, Jiachen Li, Hanwen Xing, Tianqi Zhao, Fengyuan Yu, Weihang Xiao, Yizheng Jiao, Jianheng Hou, Danyang Zhang, Pengcheng Xu, Boyang Zhong, Zehong Zhao, Gaoyun Fang, John Kitaoka, Yile Xu, Hua Xu, Kenton Blacutt, Tin Nguyen, Siyuan Song, Haoran Sun, Shaoyue Wen, Linyang He, Runming Wang, Yanzhi Wang, Mengyue Yang, Ziqiao Ma, Raphaël Millière, Freda Shi, Nuno Vasconcelos, Daniel Khashabi, Alan Yuille, Yilun Du, Ziming Liu, Bo Li, Dahua Lin, Ziwei Liu, Vikash Kumar, Yijiang Li, Lei Yang, Zhongang Cai, Hokin Deng
show all authors
ICML, 2026
I contributed two tasks evaluating object counting and physical reasoning capabilities of video-language models.
Paper Website EvalKit Dataset

Academic Service