🏢 University of Chinese Academy of Sciences

VMamba: a vision backbone achieving linear time complexity using Visual State Space (VSS) blocks and 2D Selective Scan (SS2D) for efficient visual representation.

Trajectory Diffusion (T-Diff) significantly improves object goal navigation by learning sequential planning through trajectory diffusion, resulting in more accurate and efficient navigation.

L1-norm based 3D convolution achieves competitive performance with lower energy consumption and latency compared to traditional methods, as proven through universal approximation theorem and experimen…

GR2, a novel framework, extends generative retrieval to handle multi-graded relevance, addressing limitations of existing binary-relevance approaches by enhancing docid distinctness and implementing m…

DEVIL: a novel text-to-video evaluation protocol focusing on video dynamics, resulting in more realistic video generation.

Self-supervised dual-frame fluid motion estimation achieves superior accuracy with 99% less training data, using a novel zero-divergence loss and dynamic velocimetry enhancement.

Artemis: A new MLLM excels at video-based referential understanding, accurately describing targets within complex videos using natural language questions and bounding boxes, surpassing existing models…