Amir Saeidi

I am a PhD student in CS at Arizona State University, advised by Chitta Baral in the Cognition and Intelligence Lab. My current research interests are : Exploring and enhancing the robustness of large language and vision models using reinforcement learning methods with human feedback.

Email  /  Google Scholar  /  Semantic Scholar  /  Twitter  /  GitHub

profile photo
News

  • September, 2024 - Nominated as a reviewer for the ICLR 2025 conference.
  • July, 2024 - New preprint out. UnSeenTimeQA is publicly available in the GitHub repository.
  • June, 2024 - New preprint out.
  • May, 2024 - New preprint out. More details on our website.
  • April, 2024 - New preprint out.
  • April, 2024 - Received the SCAI Conference Award.
  • April, 2024 - 1 paper accepted to CVPR 2024 workshop.
  • February, 2024 - Received the GPSA Jumpstart Research Grant.
  • October, 2024 - Received the Research Fellow position at Mayo Clinic.
  • January, 2023 - Started my PhD.

Research

Representative papers are highlighted.

lang_depth
Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step Optimization
Amir Saeidi, Shivanshu Verma*, Aswin RRV*, Chitta Baral
Under Review

Paper | Project | Code

spright
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
Md Nayem Uddin, Amir Saeidi, Divij Handa, Agastya Seth, Tran Cao Son, Eduardo Blanco, Steven R. Corman, Chitta Baral
Under Review

Paper | Code

spright
Evaluating Multimodal Large Language Models Across Distribution Shifts and Augmentations
Aayush Atul Verma*, Amir Saeidi*, Shamanthak Hegde*, Ajay Therala*, Fenil Denish Bardoliya*, Nagaraju Machavarapu*, Shri Ajay Kumar Ravindhiran*, Srija Malyala*, Agneet Chatterjee*, Yezhou Yang, Chitta Baral
CVPR workshop

Paper

spright
Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
Neeraj Varshney, Satyam Raj, Venkatesh Mishra, Agneet Chatterjee, Ritika Sarkar, Amir Saeidi, Chitta Baral
arXiv

Paper

spright
Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks
Amir Saeidi, Sivanshu Verma, Chitta Baral
Under Review

Paper


This website's source code is borrowed from Jon Barron. Much thanks!