Siheng Wang

DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection

C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection

Vision Language Models Cannot Reason About Physical Transformation

Polymorphic: Plug-and-Play Visual Token Compression for Scalable VLMs

Graph Synthetic Out-of-Distribution Exposure with Large Language Models