PhD Thesis Proposal
Scalable Vision-Language Models through Unified 2D and 3D Representations
Abstract: Vision-language models have become remarkably capable on images and short videos, yet they still struggle with two abilities central to embodied intelligence: spatial understanding and long-range temporal reasoning. A major reason is representational: today's models process videos as long sequences of 2D patches, so computation grows with observation length even when the underlying scene [...]
RI PhD Thesis Proposal – Shashwat Singh
RI CALENDAR EVENT Who: Shashwat Singh Type: RI Thesis Proposal Date: Wednesday, October 7, 2026 Time: 03:30PM - 05:00PM (ET) Location: NSH 4305 Zoom link: Here Title: Extending Robot Mobility Through Mechanical Adaptation Abstract: Unstructured terrain presents diverse challenges to robot locomotion, including obstacles, deformable surfaces, and confined passages. Terrain conditions also change with time, as [...]