4 papers
Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
Juhong Min, Lazar Valkov, Vitali Petsiuk +2
Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse…
GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining
Deen Dayal Mohan, Hossein Souri, Vitali Petsiuk +4
Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works hav…
Combinative Matching for Geometric Shape Assembly
Nahyuk Lee, Juhong Min, Junhong Lee +2
This paper introduces a new shape-matching methodology, combinative matching, to combine interlocking parts for geometric shape assembly. Previous methods for geometric assembly ty…
MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
Juhong Min, Shyamal Buch, Arsha Nagrani +2
This paper addresses the task of video question answering (videoQA) via a decomposed multi-stage, modular reasoning framework. Previous modular methods have shown promise with a si…