{"total":56,"rows":[{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307,"area":"inference"},{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281,"area":null},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"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":"2504.02732","title":"Why do LLMs attend to the first token?","created":"2025-04-03","cited_by_count":127,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2403.00824","title":"Information Flow Routes: Automatically Interpreting Language Models at Scale","created":"2024-02-27","cited_by_count":95,"area":null},{"id":"2406.11430","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","created":"2024-06-17","cited_by_count":86,"area":"inference"},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2510.06477","title":"Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin","created":"2025-10-07","cited_by_count":52,"area":null},{"id":"2505.22411","title":"Mitigating Overthinking in Large Reasoning Models via Manifold Steering","created":"2025-05-28","cited_by_count":33,"area":"lr"},{"id":"2508.12587","title":"Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models","created":"2025-08-18","cited_by_count":32,"area":"lr"},{"id":"2508.02546","title":"What are you sinking? A geometric approach on attention sink","created":"2025-08-04","cited_by_count":28,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2510.08510","title":"To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models","created":"2025-10-09","cited_by_count":20,"area":"mllm"},{"id":"2510.15731","title":"Attention Sinks in Diffusion Language Models","created":"2025-10-17","cited_by_count":20,"area":"diffusion"},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2510.22603","title":"Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs","created":"2025-10-26","cited_by_count":11,"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":"2411.07176","title":"More Expressive Attention with Negative Weights","created":"2024-11-11","cited_by_count":9,"area":null},{"id":"2511.00280","title":"Calibration Across Layers: Understanding Calibration Evolution in LLMs","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2507.03865","title":"OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference","created":"2025-07-05","cited_by_count":8,"area":"inference"},{"id":"2504.09456","title":"Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs","created":"2025-04-13","cited_by_count":7,"area":"mllm"},{"id":"2412.07334","title":"Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2509.09650","title":"All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens","created":"2025-09-11","cited_by_count":5,"area":null},{"id":"2601.21709","title":"Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis","created":"2026-01-29","cited_by_count":5,"area":"inference"},{"id":"2512.22213","title":"On the Existence and Behavior of Secondary Attention Sinks","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2602.05228","title":"Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink","created":"2026-02-05","cited_by_count":4,"area":"alignment"},{"id":"2604.03316","title":"When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models","created":"2026-04-01","cited_by_count":4,"area":"mllm"},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2503.21718","title":"Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2605.29657","title":"OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning","created":"2026-05-28","cited_by_count":3,"area":"mllm"},{"id":"2406.09140","title":"Investigating the translation capabilities of Large Language Models trained on parallel data only","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2408.00244","title":"Enhanced Structured State Space Models via Grouped FIR Filtering and Attention Sink Mechanisms","created":"2024-08-01","cited_by_count":2,"area":"ssm"},{"id":"2604.10027","title":"SinkTrack: Attention Sink based Context Anchoring for Large Language Models","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"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":"2605.17084","title":"Scale Determines Whether Language Models Organize Representation Geometry for Prediction","created":"2026-05-16","cited_by_count":2,"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":"2602.01893","title":"Geometric Analysis of Token Selection in Multi-Head Attention","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2605.06611","title":"The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.07502","title":"Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2609.11716","title":"Why Does Post-Training Quantization Work?","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2504.04238","title":"Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models","created":"2025-04-05","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":"2606.00930","title":"A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink","created":"2026-05-30","cited_by_count":0,"area":"ssm"},{"id":"2606.07604","title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","created":"2026-05-29","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":"2606.14040","title":"Decompose Sparsely Where You Should, Absorb Densely Where You Should No","created":"2026-06-12","cited_by_count":0,"area":"mechinterp"},{"id":"2607.24017","title":"Disentangling Semantic Attention from Structural Bias in the Attention Manifold","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2608.20999","title":"Latent Ordinal Evidence, Misaligned Outputs: Inference-Time Ordinal Lens Alignment for Multimodal LLMs","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"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":"2610.06012","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}],"next_cursor":null}