VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice Paper โข 2601.05175 โข Published Jan 8 โข 36
Interpret Vision Transformers as ConvNets with Dynamic Convolutions Paper โข 2309.10713 โข Published Sep 19, 2023 โข 1
EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM Paper โข 2312.06660 โข Published Dec 11, 2023 โข 1
Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively Paper โข 2401.02955 โข Published Jan 5, 2024 โข 23