244 citations · 966 across the 45 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Chongjian Ge, Hanwen Jiang, Tianyu Wang +9
Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera,…
cs.CV2026
SimpleMatch: A Simple and Strong Baseline for Semantic Correspondence
Hailing Jin, Huiying Li
Recent advances in semantic correspondence have been largely driven by the use of pre-trained large-scale models. However, a limitation of these approaches is their dependence on h…