3 papers
cs.CV2026
TERRA: A Hierarchical Parallel Training and Memory Orchestration Framework for High-Resolution AI-based Earth Modeling
Ruohan Wu, Ziqi Zhu, Yang Zhao +6
Training high-resolution AI-based Earth forecasting models is memory-intensive. Window-based Swin Transformers reduce the quadratic cost of global attention, but existing distribut…
cs.CV2026
Clore: Interactive Pathology Image Segmentation with Click-based Local Refinement
Tiantong Wang, Minfan Zhao, Jun Shi +2
Recent advancements in deep learning-based interactive segmentation methods have significantly improved pathology image segmentation. Most existing approaches utilize user-provided…
cs.LG2025
FlashOmni: A Unified Sparse Attention Engine for Diffusion Transformers
Liang Qiao, Yue Dai, Yeqi Huang +3
Multi-Modal Diffusion Transformers (DiTs) demonstrate exceptional capabilities in visual synthesis, yet their deployment remains constrained by substantial computational demands. T…