{"total":56,"rows":[{"id":"2504.19413","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","created":"2025-04-28","cited_by_count":779,"area":"agents"},{"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":"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":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2501.16383","title":"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations","created":"2025-01-25","cited_by_count":46,"area":"inference"},{"id":"2410.17897","title":"Value Residual Learning","created":"2024-10-23","cited_by_count":27,"area":"inference"},{"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":"2504.20966","title":"Softpick: No Attention Sink, No Massive Activations with Rectified Softmax","created":"2025-04-29","cited_by_count":22,"area":null},{"id":"2502.13913","title":"How Do LLMs Perform Two-Hop Reasoning in Context?","created":"2025-02-19","cited_by_count":20,"area":"lr"},{"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":"2509.23365","title":"Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought","created":"2025-09-27","cited_by_count":16,"area":"lr"},{"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":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"area":"alignment"},{"id":"2504.01928","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","created":"2025-04-02","cited_by_count":13,"area":null},{"id":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","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":"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":"2506.10887","title":"Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers","created":"2025-06-12","cited_by_count":10,"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":"2504.03889","title":"Identifying and Evaluating Inactive Heads in Pretrained LLMs","created":"2025-04-04","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":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","cited_by_count":8,"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":"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":"2602.16837","title":"A Structural Theory of Position Bias in Transformers","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"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":"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":"2604.08005","title":"Preference Redirection via Attention Concentration: An Attack on Computer Use Agents","created":"2026-04-09","cited_by_count":3,"area":"agents"},{"id":"2604.14922","title":"LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2509.16875","title":"Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2602.02470","title":"Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2603.06248","title":"Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2605.28600","title":"Transformers Provably Learn to Internalize Chain-of-Thought","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"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":"2605.08453","title":"Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2608.28383","title":"Semantic Head Specialization Guides Hybrid ViT Attention for Multimodal LLMs","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2510.11789","title":"Minimax Rates for Learning Pairwise Interactions in Attention-Style Models","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2601.03424","title":"Spectral Archaeology: The Causal Topology of Model Evolution","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2604.10496","title":"CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts","created":"2026-04-12","cited_by_count":0,"area":"moe"},{"id":"2604.11912","title":"How Transformers Learn to Plan via Multi-Token Prediction","created":"2026-04-13","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":"2605.16468","title":"Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex","created":"2026-05-15","cited_by_count":0,"area":null},{"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":"2609.22005","title":"Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.23585","title":"Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only Quantization","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.31654","title":"Temporal-Attention Head Specialization During Video Diffusion Training","created":"2026-09-14","cited_by_count":0,"area":"diffusion"},{"id":"2609.32704","title":"CoWindow Attention: Full Causal Coverage Is a Collective Property","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37879","title":"Retrieval Capacity of Self-Attention Under Competition","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38832","title":"Scaling Parameter and Context in Attention: Native Sparse Attention from Mixture-of-Head","created":"2026-09-30","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}