Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation
Damiano Marsili, Raphi Kang, Aditya Mehta +2
Mixture-of-Experts (MoE) architectures scale model capacity through sparse computation, routing each token through only a small subset of experts. In this work, we explore whether…
cs.CV2026
Training-Free Temporal Abstraction for General Video Understanding
Etienne Casanova, Sevan Brodjian, Pietro Perona
Videos are expensive to analyze frame by frame, yet many video understanding tasks depend on knowing where relevant moments occur. A system may need to find when an action changes,…
cs.CV2026
Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models
Raphi Kang, Hongqiao Chen, Georgia Gkioxari +1
Spatio-temporal reasoning is a remarkable capability of Vision Language Models (VLMs), but the underlying mechanisms of such abilities remain largely opaque. We postulate that visu…