Shahriyar Zaman Ridoy

AI Researcher · Reasoning & Reliability in Foundational Models

I am an AI researcher working on reasoning and reliability in language and vision-language models. Currently, I am a Research Intern at Vanderbilt University, a Research Assistant at Cognitive Agents and Interaction Lab (CAIL), University of Dhaka, working with Dr. Md Mosaddek Khan, and a Research Collaborator with Qatar Computing Research Institute (QCRI), working with Dr. Md Rizwan Parvez. I also collaborate with Prof. Alex Lamb (College of AI, Tsinghua University; formerly Microsoft Research).

My research spans three connected directions: (1) multimodal reasoning, including spatial, temporal, and compositional understanding; (2) formal and symbolic reasoning, drawing on automata theory to connect linguistic specification, symbolic representation, and executable computation, so that reasoning can be studied through behaviorally verifiable mechanisms; and (3) emotion understanding and trustworthy evaluation, grounded in psychological theories and human affective factors. I develop evaluation frameworks to assess emotional competence, psychological alignment, bias, and reliability. More broadly, I study when models reason and why they fail, verify their capabilities through behavioral evaluation, and develop mitigation strategies to improve their reliability.

My publications include work at NeurIPS, ICML, ICLR, EMNLP, ACM FAccT, and AACL-IJCNLP, among other venues. I serve as a reviewer for ICLR, WACV, the NeurIPS, and ICML, NeurIPS, and ACL workshops.

I graduated summa cum laude in CSE from North South University (CGPA 3.88/4.00, top 2%), and my thesis research received the Best Paper Award at IEEE IS 2024. Previously, I interned at the Artificial Intelligence Institute, University of South Carolina (AIISC), working with Dr. Amitava Das, Aman Chadha (Google DeepMind), and Vinija Jain (Google).

I am seeking PhD (or MS) positions starting Fall 2027 in reasoning, evaluation, and trustworthy multimodal NLP. If my work aligns with your group, I would be glad to hear from you at shahriyar.zaman01@gmail.com.

News and Updates

All news

  • 🎉 Our paper SEISMOS: A Statistical Signal Detection Framework for Semantic Chunking is accepted to the NeurIPS 2026 main conference (poster)!

  • Serving as a reviewer for ICLR 2027.

  • Invited to serve as a reviewer for three NeurIPS 2026 workshops: AI4MetaScience, AIWILD, and SLM-Agents.

  • Three of our papers on geo-spatial and geo-temporal reasoning, crisis sentiment analysis, and clinical NLP robustness were accepted to AACL-IJCNLP 2026 (2 Main, 1 Findings)—one as first author, one as second author, and one as a co-author.

  • Invited to serve as a reviewer for WACV 2027.

  • Two papers on formal and structured computational reasoning are accepted to Findings of EMNLP 2026, one as first author and one as co-author.

  • Attending ICML 2026 at COEX in Seoul, South Korea, to present our main-track paper, TimeSpot, along with several workshop papers.

  • Invited to serve as a reviewer for the NeurIPS 2026 Creative AI Track.

  • Three papers are accepted to ICML 2026 workshops: two at the AI for Math Workshop (AI4Math) and one at Muslims in ML (MusIML). One AI4Math paper also received a reviewer-level Best Paper nomination recommendation.

  • Serving as a reviewer for the AI for Math Workshop at ICML 2026.

  • When Machines Decide If a Human Wrote It: Creativity in the Age of AI Detectors is accepted to the ICML 2026 Workshop on Human-AI Co-Creativity.

  • TimeSpot is accepted to the ICML 2026 main track, with me as co-first author, in collaboration with QCRI and CIOL. Read more

  • BengaliMoralBench, the first large-scale ethics benchmark for the Bengali language and culture, is accepted to ACM FAccT 2026, in collaboration with CIOL and Hanyang University.

  • SpatiaLab is accepted to ICLR 2026, in collaboration with QCRI, Monash University, and CIOL. Read more

Selected Publications

All publications
Publication snapshot As of September 2026 · 15 peer-reviewed papers
12
Conference papers
8 as first or co-first author
NeurIPS 2026ICML 2026ICLR 2026EMNLP 2026 ×2ACM FAccT 2026AACL-IJCNLP 2026 ×3EMNLP 2025IEEE BigData 2024IEEE IS 2024 · Best Paper
1
Journal article
Springer Nature
SN Computer Science 2025
2
Workshop papers
Human-AI Co-Creativity, SLM evaluation
ICML 2026NeurIPS 2026
4
Under review
1 as co-first author
ICLR 2027ACL Rolling ReviewArray (Elsevier)

* denotes equal contribution. See all 17 papers with abstracts and BibTeX.

Research Experience

Full experience

Technical Skills

Programming
Python, C++, C, Java, SQL
ML frameworks
PyTorch, TensorFlow / Keras, Hugging Face Transformers and Datasets, scikit-learn, NumPy, Pandas, Matplotlib
Methods
Benchmark design and large-scale evaluation of LLMs and vision-language models, zero-shot and prompt-based pipelines, knowledge distillation and model compression, ensemble stacking, hallucination detection, adversarial robustness, transformer fine-tuning, behavioral evaluation of generated formal systems (grammars, automata, Turing machines)
Tooling
Git, Docker, LaTeX
Languages
English, Bangla (native)

Academic Service

All service

Peer Review

  • ICLR 2027
  • WACV 2027
  • NeurIPS 2026, Creative AI Track
  • NeurIPS 2026 AI4MetaScience Workshop
  • NeurIPS 2026 AIWILD Workshop
  • NeurIPS 2026 SLM-Agents Workshop
  • AI for Math Workshop, ICML 2026
  • ACL 2025 Student Research Workshop

Teaching

  • Lab Instructor, Department of Electrical and Computer Engineering, North South University Feb 2025 – Dec 2025
  • Teaching Assistant, North South University Feb 2023 – Jan 2025

Talks and Community

  • Presented TimeSpot and workshop papers at ICML 2026, Seoul Jul 2026
  • Lab Instructor Coordinator for CSE 225L, standardizing labs across sections
  • Mentored peers in data structures and algorithms with NSU Problem Solvers 2021 – 2023

I am always happy to talk about research, collaborations, and PhD opportunities. Email is the best way to reach me. Contact details.