Tejas Polu's Logo

Research

Exploring the frontiers of machine learning and artificial intelligence through innovative research and practical applications.

Research Interests

Multimodal LLMs

Building and evaluating models that understand and generate across text, vision, and more.

Human-in-the-Loop

Combining human feedback with automated AI learning to shape behavior and ensure reliability.

AI for Accessibility

Developing adaptive ML methods to expand access and meet diverse needs effectively in practice.

Publications

IUI 2026 Workshop
IUI

Annota: Crowdsourced Predictions for Crowd Convergence

Samintha Chandrasiri*, Neo Sud*, Tejas Polu, Emil Wilson, Brian Nguyen, David T. Lee

Submitted to IUI 2026 (under review)

🏆 Dean's Undergraduate Research Award

ICML 2025 Workshop
ICML

CCC: Enhancing Video Generation via Structured MLLM Feedback

Jing Gu, Ashwin Nagarajan, Tejas Polu, Kaizhi Zheng, Ruijian Zha, Jie Yang, Xin Eric Wang

Second Workshop on Test-Time Adaptation: Putting Updates to the Test! at ICML 2025

PDF
CHI 2025 Workshop
CHI

Human-centered World Modeling: Enhancing Multi-Agent AI Adaptability

Reza Habibi, Zhiyu Lin, Jiahong Li, Tejas Polu, Ashwin Nagarajan, Magy Seif El-Nasr

CHI 2025: Human-AI Interaction for Augmented Reasoning

PDF