group 2024 banner
header-image_0001_layer_4.jpg
header-image_0003_layer_0.jpg
header-image_0002_layer_1.jpg

Two papers in NeurIPS 2025 from VLG Researchers!

VLG researchers will be presenting papers on LLM reasoning and in-context learning

VLG authors are presenting 2 papers at NeurIPS 2025.

1. Manyi Yao is the first author on a paper that shows how spatial grounding helps with improved LLM reasoning. Details can be found in the pre-print below:-
iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning, M. Yao, B. Zhuang, S. Garg, A. Roy-Chowdhury, C. Shelton, M. Chandraker, A. Aich.

2. VLG Researchers are also collaborators on a paper that studies the properties of in-context learning using unlabeled data.
When and How Unlabeled Data Provably Improve In-context Learning, Y. Li, X. Chang, M. Kara, X. Liu, A. Roy-Chowdhury, S. Oymak.