← Search

Haodong Qian

2 accepted papers

2025

Bi-Directional Multi-Scale Graph Dataset Condensation via Information Bottleneck

AAAI 2025technical

Dataset condensation has significantly improved model training efficiency, but its application on devices with different computing power brings new requirements for different data sizes. For sparse graph data with non-Euclidean structures, repeated condensation of each scale may lead to significant…

2025

Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding

CVPR 2025highlight

Modern vision-language models (VLMs) develop patch embedding and convolution backbone within vector space, especially Euclidean ones, at the very founding. When expanding VLMs to a galaxy-scale for understanding astronomical phenomena, the integration of spherical space for planetary orbits and hype…

Cited by 0SourcePDFScholar