{"total":67,"rows":[{"id":"2503.03321","title":"See What You Are Told: Visual Attention Sink in Large Multimodal Models","created":"2025-03-05","cited_by_count":132,"area":"mllm"},{"id":"2410.19258","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","created":"2024-10-25","cited_by_count":97,"area":"lr"},{"id":"2503.06287","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding","created":"2025-03-08","cited_by_count":83,"area":"mllm"},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2503.17349","title":"Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2412.18108","title":"Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach","created":"2024-12-24","cited_by_count":35,"area":"mllm"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21,"area":"lr"},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2410.12409","title":"Revealing the Barriers of Language Agents in Planning","created":"2024-10-16","cited_by_count":20,"area":"agents"},{"id":"2505.13737","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","created":"2025-05-19","cited_by_count":16,"area":null},{"id":"2504.18574","title":"Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism","created":"2025-04-22","cited_by_count":15,"area":null},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"area":"mllm"},{"id":"2504.13752","title":"Learning to Attribute with Attention","created":"2025-04-18","cited_by_count":13,"area":null},{"id":"2505.11739","title":"ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training","created":"2025-05-16","cited_by_count":12,"area":null},{"id":"2504.01100","title":"Repetitions are not all alike: distinct mechanisms sustain repetition in language models","created":"2025-04-01","cited_by_count":10,"area":null},{"id":"2508.20412","title":"MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning","created":"2025-08-28","cited_by_count":10,"area":"agents"},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2509.17588","title":"Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models","created":"2025-09-22","cited_by_count":9,"area":"mllm"},{"id":"2509.24745","title":"ProxyAttn: Guided Sparse Attention via Representative Heads","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8,"area":null},{"id":"2602.22424","title":"Causality $\\neq$ Invariance: Function and Concept Vectors in LLMs","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2501.07890","title":"GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism","created":"2025-01-14","cited_by_count":7,"area":"lr"},{"id":"2502.09647","title":"Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification","created":"2025-02-11","cited_by_count":5,"area":null},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2510.10071","title":"ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2512.10978","title":"Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning","created":"2025-12-03","cited_by_count":5,"area":"lr"},{"id":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"area":"mechinterp"},{"id":"2603.13782","title":"Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation Detection","created":"2026-03-14","cited_by_count":5,"area":"vla"},{"id":"2603.29979","title":"Structural Feature Engineering for Generative Engine Optimization: How Content Structure Shapes Citation Behavior","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2410.13957","title":"Goal Inference from Open-Ended Dialog","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2601.18110","title":"AttenMIA: LLM Membership Inference Attack through Attention Signals","created":"2026-01-26","cited_by_count":4,"area":"safety"},{"id":"2603.20662","title":"Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning","created":"2026-03-21","cited_by_count":4,"area":"lr"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2506.01215","title":"Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers","created":"2025-06-01","cited_by_count":3,"area":"inference"},{"id":"2506.15617","title":"The Compositional Architecture of Regret in Large Language Models","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2509.24169","title":"Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2602.11528","title":"Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2604.06005","title":"Disentangling MLP Neuron Weights in Vocabulary Space","created":"2026-04-07","cited_by_count":3,"area":"mechinterp"},{"id":"2604.15701","title":"Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information","created":"2026-04-17","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2508.12863","title":"Word Meanings in Transformer Language Models","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2508.20353","title":"DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2509.24164","title":"Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.19875","title":"Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention","created":"2025-10-22","cited_by_count":2,"area":"mechinterp"},{"id":"2512.10300","title":"Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2603.03335","title":"Compressed Sensing for Capability Localization in Large Language Models","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2606.24467","title":"CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference","created":"2026-06-23","cited_by_count":2,"area":"inference"},{"id":"2607.11875","title":"Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks","created":"2026-07-13","cited_by_count":2,"area":"lr"},{"id":"2410.02343","title":"Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2603.02919","title":"Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers","created":"2026-03-03","cited_by_count":1,"area":"diffusion"},{"id":"2606.15821","title":"The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages","created":"2026-06-14","cited_by_count":1,"area":"mllm"},{"id":"2411.10334","title":"Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2505.24292","title":"Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.07501","title":"Graph-of-Causal Evolution: Challenging Chain-of-Model for Reasoning","created":"2025-06-09","cited_by_count":0,"area":"lr"},{"id":"2508.00285","title":"Enhancing Trustworthy Clinical Diagnosis Decision-Making in Large Language Models via Etiology-Aware Attention Supervision","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2510.11390","title":"Medical Interpretability and Knowledge Maps of Large Language Models","created":"2025-10-13","cited_by_count":0,"area":"mechinterp"},{"id":"2512.05385","title":"ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2604.03764","title":"Automated Attention Pattern Discovery at Scale in Large Language Models","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.20410","title":"Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2606.06840","title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.13425","title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.25873","title":"How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.33851","title":"Rethinking Contextualization by Reinterpreting Attention Head Channels","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.04676","title":"Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}