Hunar Batra

Hunar Batra is a DPhil (PhD) student in Computer Science at the University of Oxford (2023-2026), affiliated with Wolfson College and supervised by Ronald Clark. Her research focuses on multimodal learning, interpretability, and AI alignment. She has co-authored published work on bias mitigation in chain-of-thought reasoning (Bias-Augmented Consistency Training, with researchers from Anthropic and NYU) and on continual learning (EVCL, presented at the ICML 2024 Workshop on Structured Probabilistic Inference). She serves as a consultant at Anthropic and as a visiting researcher at the NYU Center for Data Science, and has previously worked at the UK AI Security Institute and METR. She received the Google Women in Computer Science Generation Scholarship in 2022 while completing her MSc at Oxford. Her PhD is supported in part by a Long-Term Future Fund grant covering tuition and living expenses to accelerate alignment research using expert iteration and Human-AI collaboration tools.

No endorsements yet.

Personal Website

https://hunarbatra.com/

LinkedIn

LinkedIn

Twitter / X

Twitter

LessWrong

-

EA Forum

-