{"total":208,"rows":[{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2506.15841","title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","created":"2025-06-18","cited_by_count":238,"area":"lr"},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187,"area":"diffusion"},{"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":"2502.01951","title":"On the Emergence of Position Bias in Transformers","created":"2025-02-04","cited_by_count":59,"area":null},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"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":"2506.08010","title":"Vision Transformers Don't Need Trained Registers","created":"2025-06-09","cited_by_count":41,"area":null},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2604.11791","title":"A Mechanistic Analysis of Looped Reasoning Language Models","created":"2026-04-13","cited_by_count":33,"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":"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":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"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":"2502.18845","title":"Sliding Window Attention Training for Efficient Large Language Models","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2504.20966","title":"Softpick: No Attention Sink, No Massive Activations with Rectified Softmax","created":"2025-04-29","cited_by_count":22,"area":null},{"id":"2604.04921","title":"TriAttention: Efficient Long Reasoning with Trigonometric KV Compression","created":"2026-04-06","cited_by_count":21,"area":"lr"},{"id":"2505.18132","title":"BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models","created":"2025-05-23","cited_by_count":20,"area":null},{"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":"2601.20499","title":"Efficient Autoregressive Video Diffusion with Dummy Head","created":"2026-01-28","cited_by_count":20,"area":"diffusion"},{"id":"2602.13515","title":"SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning","created":"2026-02-13","cited_by_count":18,"area":"diffusion"},{"id":"2609.01343","title":"SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers","created":"2026-09-01","cited_by_count":18,"area":"moe"},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2502.00919","title":"Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings","created":"2025-02-02","cited_by_count":16,"area":null},{"id":"2503.08908","title":"Interpreting the Repeated Token Phenomenon in Large Language Models","created":"2025-03-11","cited_by_count":16,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2504.10317","title":"Analysis of Attention in Video Diffusion Transformers","created":"2025-04-14","cited_by_count":15,"area":"diffusion"},{"id":"2502.14317","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","created":"2025-02-20","cited_by_count":14,"area":"inference"},{"id":"2410.13846","title":"LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation","created":"2024-10-17","cited_by_count":12,"area":"lr"},{"id":"2411.15236","title":"Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps","created":"2024-11-21","cited_by_count":12,"area":"diffusion"},{"id":"2501.12959","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","created":"2025-01-22","cited_by_count":12,"area":"inference"},{"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":"2507.07814","title":"Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers","created":"2025-07-10","cited_by_count":11,"area":null},{"id":"2510.02295","title":"VideoNSA: Native Sparse Attention Scales Video Understanding","created":"2025-10-02","cited_by_count":11,"area":"mllm"},{"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":"2507.16018","title":"Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers","created":"2025-07-21","cited_by_count":10,"area":null},{"id":"2503.02003","title":"HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs","created":"2025-03-03","cited_by_count":9,"area":"lr"},{"id":"2510.10276","title":"Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMs","created":"2025-10-11","cited_by_count":9,"area":null},{"id":"2605.23889","title":"HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction","created":"2026-05-22","cited_by_count":9,"area":null},{"id":"2504.03889","title":"Identifying and Evaluating Inactive Heads in Pretrained LLMs","created":"2025-04-04","cited_by_count":8,"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":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2510.09017","title":"Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2512.21338","title":"HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming","created":"2025-12-24","cited_by_count":8,"area":"diffusion"},{"id":"2602.21445","title":"VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policies","created":"2026-02-24","cited_by_count":8,"area":"vla"},{"id":"2506.18226","title":"Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation","created":"2025-06-23","cited_by_count":7,"area":"inference"},{"id":"2601.19895","title":"Post-LayerNorm Is Back: Stable, ExpressivE, and Deep","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2603.00510","title":"What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models","created":"2026-02-28","cited_by_count":7,"area":"mllm"},{"id":"2502.13946","title":"Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region","created":"2025-02-19","cited_by_count":6,"area":"alignment"},{"id":"2503.15450","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2505.18605","title":"Rethinking Causal Mask Attention for Vision-Language Inference","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"id":"2510.17021","title":"Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning","created":"2025-10-19","cited_by_count":6,"area":"safety"},{"id":"2601.05866","title":"FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG","created":"2026-01-09","cited_by_count":6,"area":"rag"},{"id":"2601.07036","title":"Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2603.14337","title":"On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs","created":"2026-03-15","cited_by_count":6,"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":"2505.17083","title":"Scale-invariant Attention","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2508.14067","title":"Punctuation and Predicates in Language Models","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2511.09146","title":"DoPE: Denoising Rotary Position Embedding","created":"2025-11-12","cited_by_count":5,"area":null},{"id":"2601.02993","title":"Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation","created":"2026-01-06","cited_by_count":5,"area":"rag"},{"id":"2601.07894","title":"Revealing the Attention Floating Mechanism in Masked Diffusion Models","created":"2026-01-12","cited_by_count":5,"area":"diffusion"},{"id":"2601.21709","title":"Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis","created":"2026-01-29","cited_by_count":5,"area":"inference"},{"id":"2602.01203","title":"Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse","created":"2026-02-01","cited_by_count":5,"area":"moe"},{"id":"2602.04268","title":"KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing","created":"2026-02-04","cited_by_count":5,"area":"mllm"},{"id":"2604.17087","title":"EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling","created":"2026-04-18","cited_by_count":5,"area":"mllm"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2502.00281","title":"Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective","created":"2025-02-01","cited_by_count":4,"area":"moe"},{"id":"2505.24244","title":"Mamba Knockout for Unraveling Factual Information Flow","created":"2025-05-30","cited_by_count":4,"area":"ssm"},{"id":"2508.03668","title":"CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2508.17807","title":"Attention Debiasing for Token Pruning in Vision Language Models","created":"2025-08-25","cited_by_count":4,"area":"mllm"},{"id":"2512.22213","title":"On the Existence and Behavior of Secondary Attention Sinks","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2601.19657","title":"One Token Is Enough: Improving Diffusion Language Models with a Sink Token","created":"2026-01-27","cited_by_count":4,"area":"diffusion"},{"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":"2605.30010","title":"EarlyTom: Early Token Compression Completes Fast Video Understanding","created":"2026-05-28","cited_by_count":4,"area":"inference"},{"id":"2607.19139","title":"Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers","created":"2026-07-21","cited_by_count":4,"area":"diffusion"},{"id":"2607.27110","title":"FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring","created":"2026-07-29","cited_by_count":4,"area":"diffusion"},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2504.17562","title":"When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2505.24179","title":"SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2507.04239","title":"Scaling Context Requires Rethinking Attention","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2507.04404","title":"LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2601.00919","title":"Attention Needs to Focus: A Unified Perspective on Attention Allocation","created":"2026-01-01","cited_by_count":3,"area":null},{"id":"2601.01224","title":"Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment","created":"2026-01-03","cited_by_count":3,"area":"diffusion"},{"id":"2601.08273","title":"HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding","created":"2026-01-13","cited_by_count":3,"area":"inference"},{"id":"2602.23057","title":"Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.06591","title":"What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs","created":"2026-02-04","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":"2605.09313","title":"Attention Sinks in Diffusion Transformers: A Causal Analysis","created":"2026-05-10","cited_by_count":3,"area":"diffusion"},{"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":"2605.29657","title":"OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning","created":"2026-05-28","cited_by_count":3,"area":"mllm"},{"id":"2606.05404","title":"Harnessing Generalist Agents for Contextualized Time Series","created":"2026-06-03","cited_by_count":3,"area":"agents"},{"id":"2606.19005","title":"Sumi: Open Uniform Diffusion Language Model from Scratch","created":"2026-06-17","cited_by_count":3,"area":"diffusion"}],"next_cursor":"100"}