attention pattern

ART: Attention Replacement Technique to Improve Factuality in LLMs ACL 2026 Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs ACL 2026 Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations CVPR 2026 Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models ACL 2026 Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data AAAI 2026 HiPrune: Training-Free Visual Token Pruning via Hierarchical Attention in Vision-Language Models (Student Abstract) AAAI 2026 Look-Back: Implicit Visual Re-focusing in MLLM Reasoning AAAI 2026 Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis EACL 2026 Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation AAAI 2026 RegNLI: Detecting Online Product Misbranding through Legal and Linguistic Alignment EACL 2026 Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking ACL 2026 Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns ACL 2025 Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers ICLR 2025 Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax NAACL 2025 Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models ICLR 2025 FADE: Frequency-Aware Diffusion Model Factorization for Video Editing CVPR 2025 Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities CVPR 2025 (How) Can Transformers Predict Pseudo-Random Numbers? ICML 2025 How to Make LLMs Forget: On Reversing In-Context Knowledge Edits NAACL 2025 Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference ICLR 2025 Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis EMNLP 2025 Position: We Need An Algorithmic Understanding of Generative AI ICML 2025 Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs EMNLP 2025 Sparse Latents Steer Retrieval-Augmented Generation ACL 2025 UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation ICLR 2025