{"total":33,"rows":[{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2603.11487","title":"Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2601.06787","title":"Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning","created":"2026-01-11","cited_by_count":8,"area":null},{"id":"2601.10266","title":"Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2512.22213","title":"On the Existence and Behavior of Secondary Attention Sinks","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2602.01572","title":"LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2603.06922","title":"NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2603.17771","title":"Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2605.12922","title":"When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.23033","title":"Uncovering the Latent Potential of Deep Intermediate Representations","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2605.08504","title":"A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2604.12128","title":"Phantom Paradoxes: Language Models Treat Unresolved Circular Truth Dependence as Contradiction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.08453","title":"Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.18246","title":"Variable-Width Transformers","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2608.01816","title":"Divergent large language model predictions from convergent representations in ambiguous word pairs","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2510.13860","title":"ShishuLM : Achieving Optimal and Efficient Parameterization with Low Attention Transformer Models","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2601.08131","title":"Attention Projection Mixing with Exogenous Anchors","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2604.10697","title":"Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.14722","title":"A Mechanistic Account of Attention Sinks in GPT-2: One Circuit, Broader Implications for Mitigation","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.09213","title":"Kinetic theory for Transformers and the lost-in-the-middle phenomenon","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.10503","title":"SLASH the Sink: Sharpening Structural Attention Inside LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.08105","title":"A Unifying View of Attention Sinks: From Mechanisms to Architectural Interventions","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.28959","title":"Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.09085","title":"It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.31098","title":"The Residual Stream's Effective Depth","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31956","title":"Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32100","title":"Emergent One-Third Scaling Law as Attention Tries to Concentrate","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32712","title":"MassAlloc Attention: Let Attention Allocate Its Own Compute","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35630","title":"Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.05488","title":"Underscoring the Problem: Why Softpick Fails at Initialization","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.06012","title":"Spectral Geometry of Attention: From Information Routing to Uncertainty","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16745","title":"Before Attention Sinks Form: Hidden-State Geometry Reveals and Modulates Their Formation","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19324","title":"Why don't Graph Transformers attend to the same token?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}