Exploring the frontiers of machine learning and artificial intelligence through innovative research and practical applications.
Building safer LLMs via evaluation, alignment, and red-teaming to mitigate misuse and failures.
Building and evaluating models that understand and generate across text, vision, and other modalities.
Integrating human feedback with automated learning to steer model behavior and safeguard reliability.
Kaiwen Zhou, Shreedhar Jangam*, Ashwin Nagarajan*, Tejas Polu*, Suhas Oruganti, Chengzhi Liu, Ching-Chen Kuo, Yuting Zheng, Sravana Narayanaraju, Xin Eric Wang
arXiv:2601.06663, 2026
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
Reza Habibi, Zhiyu Lin, Jiahong Li, Tejas Polu, Ashwin Nagarajan, Magy Seif El-Nasr
CHI 2025: Human-AI Interaction for Augmented Reasoning