Khyathi Raghavi Chandu

I am a Research Scientist in the Mosaic team working with Yejin Choi and the group at the Allen Institute for AI. Prior to this, I worked as a Research Scientist at Meta AI after completing my Ph.D. from Carnegie Mellon University on grounded multimodal long-form generation from the Language Technologies Institute advised by Alan W. Black, Eric Nyberg and Yonatan Bisk. My current focus is centered on three primary pillars:

• Uncertainty and Hallucinations: Improving reliability and awareness in LLMs and VLMs with a focus on reducing hallucinations in unimodal and multimodal scenarios.
• Interactive Agents for reasoning and generation: Teaching machines to plan and execute complex interactive tasks. Syngergizing LLMs and VLMs to assist each other.
• Evaluating RL: Understanding and evaluating the capabilities of LLMs especially in the wild and reward models.

I am also excited about inference time algorithms, multilinguality and alignment. Get in touch if you want to chat, I’m open to collaborations or brainstorming!

I am fortunate to have been selected as a Rising Star by UC Berkeley. I am very passionate about DEI and co-chaired Academic Inclusion sub-committee multiple years at ACL 2020, ACL 2021, NAACL 2022 and co-organized Widening NLP in 2020 and 2021. I am very active in participating in community activities, organized several *CL workshops at conferences and served as Area Chair at COLM 2024, ACL ARR (Feb, Apr, June) 2024, and AACL 2023. I am fortunate to have worked with amazing researchers in my past internships at Google, Apple and Meta.