AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Paper • 2603.28696 • Published • 6
None defined yet.
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control