Attention

AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM CVPR 2026 Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow CVPR 2026 Attention Basin: Why Contextual Position Matters in Large Language Models ACL 2026 Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks ACL 2026 Attention-to-Survival: Multimodal Fracture Risk Prediction Based on Pelvic Radiographs and Clinical Data from the Study of Osteoporotic Fractures MIDL 2026 Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs ACL 2026 AttnPO: Attention-Guided Process Supervision for Efficient Reasoning ACL 2026 AVGGT: Rethinking Global Attention for Accelerating VGGT CVPR 2026 Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes CVPR 2026 Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval CVPR 2026 Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding CVPR 2026 Challenging the Explanation Based on Preceding Tokens: Discovering Transferable Non-Literal Biasing ACL 2026 CoreGaze: Core Subgraph-Driven Visual Gaze Diffusion for Training-Free Referring Multimodal Large Language Models ACL 2026 Cross-Modal Attention Calibration for LVLM Hallucination Mitigation CVPR 2026 Curvature-Aware Captioning: Leveraging Geodesic Attention for 3D Scene Understanding CVPR 2026 Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models CVPR 2026 Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations ACL 2026 Exploring Attention Attractors in Large Language Models ACL 2026 Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing ACL 2026 GazeShift: Unsupervised Gaze Estimation and Dataset for VR CVPR 2026 GFRRN: Explore the Gaps in Single Image Reflection Removal CVPR 2026 KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing CVPR 2026 Learning Informative Attention Weights for Person Re-Identification UAI 2026 LoL: Longer than Longer, Scaling Video Generation to Hour CVPR 2026 Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement ACL 2026