Attention Mechanism

From Logical to Computational Sparsity: Structure-Aware Block-Sparse Attention for Long-Code Completion ACL 2026 Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs ACL 2026 Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation CVPR 2026 Hilbert Curve-Based Attention Enabling Topology-Preserving Image Tensor Representation for Semantic Segmentation Network CVPR 2026 HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives CVPR 2026 HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image CVPR 2026 Improving Sparse Autoencoder with Dynamic Attention CVPR 2026 Latent Attention Denoising: A Training-Free Energy-Based Framework for Mitigating Hallucinations in Vision-Language Models ACL 2026 Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers CVPR 2026 LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning ACL 2026 Learned Image Compression via Sparse Attention and Adaptive Frequency CVPR 2026 Learning Informative Attention Weights for Person Re-Identification UAI 2026 LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026 MARSS: Radar Semantic Segmentation via Modular Attention and State Space Models CVPR 2026 MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers ACL 2026 Mitigating Tokenization-Induced Distance Distortion in Long-Context Multilingual Machine Translation ACL 2026 MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On CVPR 2026 MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing CVPR 2026 Native Hybrid Attention for Efficient Sequence Modeling ACL 2026 Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection JMLR 2026 OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives CVPR 2026 Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression CVPR 2026 PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs CVPR 2026 PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction CVPR 2026 PICT at SemEval-2026 Task 3: A Transformer-Based System for Dimensional Aspect-Aware Sentiment Regression with Weighted Layer Pooling SemEval 2026