local attention

Characterizing the Expressivity of Local Attention in Transformers ACL 2026 UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders CVPR 2026 GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation AAAI 2025 MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer ICLR 2025 SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation CVPR 2025 Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding AAAI 2024 CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers AAAI 2024 CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data CVPR 2024 HomoFormer: Homogenized Transformer for Image Shadow Removal CVPR 2024 Are More Layers Beneficial to Graph Transformers? ICLR 2023 AutoFocusFormer: Image Segmentation off the Grid CVPR 2023 Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution CVPR 2023 Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers ICCV 2023 EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation ICCV 2023 From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-resolution AAAI 2023 Improving Chinese Pop Song and Hokkien Gezi Opera Singing Voice Synthesis by Enhancing Local Modeling EMNLP 2023 When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants ACL 2023 Boosting Crowd Counting via Multifaceted Attention CVPR 2022 KNN Local Attention for Image Restoration CVPR 2022 Learned Queries for Efficient Local Attention CVPR 2022 Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns ACL 2022 On the Connection between Local Attention and Dynamic Depth-wise Convolution ICLR 2022 On the Locality of Attention in Direct Speech Translation ACL 2022 RegionViT: Regional-to-Local Attention for Vision Transformers ICLR 2022 Simple Local Attentions Remain Competitive for Long-Context Tasks NAACL 2022