{"total":20,"rows":[{"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":"2604.10098","title":"Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation","created":"2026-04-11","cited_by_count":11,"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":"2606.02288","title":"Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2608.12149","title":"Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2605.17659","title":"Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2606.20743","title":"Massive Activations Are Architecturally Robust: A Controlled Scratch/Commitment Residual Stream Test","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.11805","title":"Hybrid Gated Attention","created":"2026-08-12","cited_by_count":1,"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":"2605.05686","title":"Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.03712","title":"When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.05880","title":"Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2609.13846","title":"Affinity-Aware Sharding for Delayed Tensor Parallelism","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.17599","title":"Structure is not mechanism: high-gain gated-FFN rows across text and genomic foundation models","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.22005","title":"Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention","created":"2026-09-18","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":"2609.35630","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":"2609.37040","title":"Selecting The Most Informative Tokens in Natural Language Autoencoders","created":"2026-09-29","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":"2610.07661","title":"Massive Activation Gating Channel in Large Language Models","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}