work

Working on search and reasoning with Large Language Models (LLMs). Focusing on the Deep Research (DR) paradigm, where LLM systems perform structured search over large corpora, and developing methods for claim verification and steering search processes.

Benchmarked vision-language models on inferring the message in rhetorical and atypical imagery used in advertisements, through three novel tasks. Found that VLMs struggle with reasoning about atypicality, but simple methods enable atypicality-aware verbalization and improve rhetorical image understanding.

Worked on modelling and simulating human behavior at scale from Youtube Videos. Trained multimodal LLM architectures that integrated video and textual representations, achieving significant performance gains and surpassing GPT-4 on multiple behavior prediction tasks. Published at ICLR 2024, with a spotlight presentation.