
Glimpse from the Lab: VideoCartridges
Distilling spatiotemporal context into compact, reusable representations for efficient long-video understanding
Research highlights and deep dives.

Distilling spatiotemporal context into compact, reusable representations for efficient long-video understanding

Data-free LoRA indexing and dynamic adaptation for open-vocabulary semantic segmentation under real-world domain shifts

VocAlign: A framework for source-free domain adaptation in open-vocabulary segmentation

An approach to retrieve and merge LoRA adpapters for new domains

Real-Time Adaptation for Semantic Segmentation
March 18, 2023
Browse other categories