multi-head attention

CoFact: Dynamic Coordination of Attention Heads for Improving Factual Consistency in LLMs AAAI 2026 EdgeFormer: Latency-Aware Collaborative Multi-Head Attention of Transformer Inference in Edge Networks ACL 2026 EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems ACL 2026 HTTM: Head-wise Temporal Token Merging for Faster VGGT CVPR 2026 LightGazeNet: A Lightweight GNN-based Architecture for Gaze Estimation WACV 2026 Redundancy-optimized Multi-head Attention Networks for Multi-view Multi-label Feature Selection AAAI 2026 SCOPE: Boosting LLM Efficiency with Scoped Position Encoding ACL 2026 The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms AAAI 2026 Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Interspeech 2025 Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers ICML 2025 Devil is in the Uniformity: Exploring Diverse Learners within Transformer for Image Restoration ICCV 2025 Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens CVPR 2025 DIH-CLIP: Unleashing the Diversity of Multi-Head Self-Attention for Training-Free Open-Vocabulary Semantic Segmentation ICCV 2025 HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution CVPR 2025 Incepto@DravidianLangTech 2025: Detecting Abusive Tamil and Malayalam Text Targeting Women on YouTube NAACL 2025 INFOTEC-NLP at SemEval-2025 Task 11: A Case Study on Transformer-Based Models and Bag of Words SemEval 2025 Layer Duplication in LLMs EMNLP 2025 Length Representations in Large Language Models EMNLP 2025 MagicMask: A Fast and High-fidelity Face Swapping Method Robust to Face Pose ACML 2025 MA-RAG: Automating Role Engineering for RESTful APIs with Multi-Head Attention and Retrieval-Augmented Generation IJCAI 2025 Memorization in Attention-only Transformers AISTATS 2025 MoH: Multi-Head Attention as Mixture-of-Head Attention ICML 2025 MossNet: Mixture of State-Space Experts is a Multi-Head Attention IJCNLP 2025 Olica: Efficient Structured Pruning of Large Language Models without Retraining ICML 2025 Superiority of Multi-Head Attention: A Theoretical Study in Shallow Transformers in In-Context Linear Regression AISTATS 2025