Attention Mechanism

Precise Object and Effect Removal with Adaptive Target-Aware Attention CVPR 2026 Random Wins All: Rethinking Grouping Strategies for Vision Tokens CVPR 2026 Reading As Humans: Unified Negation Detection via Cascade Linear Attention Network with Model-Agnostic Meta-Learning UAI 2026 REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression ACL 2026 ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding CVPR 2026 RegionFuse: Region-Adaptive Pixel Distribution Learning for Infrared and Visible Image Fusion CVPR 2026 Robertha: Eigenspectrum Regularized Attention for Robust Natural Language Understanding ACL 2026 Selection-as-Nonlinearity: Bridging Attention and Activation via a Joint Game-Decision Lens for Interpretable, Discriminative Visual Representations CVPR 2026 Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis ACL 2026 SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration CVPR 2026 Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling ACL 2026 SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls CVPR 2026 TAR: Token-Aware Refinement for Fine-grained Generalized Category Discovery CVPR 2026 Team BOBW (Best Of Both Worlds) at SemEval-2026 Task 3: Modular Cross-Attention Encoders for Dimensional Aspect-Based Sentiment Analysis SemEval 2026 Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context ACL 2026 The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy CVPR 2026 Thermometer of Thoughts: Enhancing LLM’s Exploration via Attention Temperature Modulation ACL 2026 Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling ACL 2026 UIKA: Fast Universal Head Avatar from Pose-Free Images CVPR 2026 UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition CVPR 2026 VMonarch: Efficient Video Diffusion Transformers with Structured Attention CVPR 2026 Why "Classic" Transformers Are Shallow and A Depth-Enabling Technique JMLR 2026 ZYC at SemEval-2026 Task 5: Application of BERT-based Contextual Embeddings Similarity for WSD SemEval 2026 Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Interspeech 2025 Acoustic Detection of UAV Abnormality Using One Ground-Based Acoustic Vector Sensor Interspeech 2025