Attention Mechanism

FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer Interspeech 2025 Forgetting Transformer: Softmax Attention with a Forget Gate ICLR 2025 HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models ACL 2025 Hierarchical Attention Generates Better Proofs ACL 2025 Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning CVPR 2025 If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation? ACL 2025 Imitating Radiological Scrolling: A Glocal-Lobal Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification MIDL 2025 Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions ICLR 2025 Improving Cross-Attention based on Positional Alignment during Inference for Robust Long-form Speech Recognition Interspeech 2025 Interactive Fusion of Multi-View Speech Embeddings via Pretrained Large-Scale Speech Models for Speech Emotional Attribute Prediction in Naturalistic Conditions Interspeech 2025 Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs AAAI 2025 Lightweight and Robust Multi-Channel End-to-End Speech Recognition with Spherical Harmonic Transform Interspeech 2025 Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs ACL 2025 LUV-Net: Multi-Pattern Lung Ultrasound Video Classification through Pattern-Specific Attention with Efficient Temporal Feature Extraction MIDL 2025 MagNet: Multi-Level Attention Graph Network for Predicting High-Resolution Spatial Transcriptomics MIDL 2025 MAIS: Memory-Attention for Interactive Segmentation MIDL 2025 Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion AISTATS 2025 Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention ACL 2025 PCA-YOLO: A Small Liver Tumor Detection Model with Patch-Contrastive Attention MIDL 2025 Pitch Contour Model (PCM) with Transformer Cross-Attention for Speech Emotion Recognition Interspeech 2025 Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction Interspeech 2025 Quantifying Logical Consistency in Transformers via Query-Key Alignment EMNLP 2025 Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking EMNLP 2025 Radar: Fast Long-Context Decoding for Any Transformer ICLR 2025 ResCLIP: Residual Attention for Training-free Dense Vision-language Inference CVPR 2025