{"total":131,"rows":[{"id":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"id":"2511.02817","title":"Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities","created":"2025-11-04","cited_by_count":40,"area":null},{"id":"2508.15734","title":"Measuring the environmental impact of delivering AI at Google Scale","created":"2025-08-21","cited_by_count":32,"area":null},{"id":"2509.23094","title":"d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching","created":"2025-09-27","cited_by_count":25,"area":"inference"},{"id":"2501.19392","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","created":"2025-01-31","cited_by_count":24,"area":"inference"},{"id":"2604.04921","title":"TriAttention: Efficient Long Reasoning with Trigonometric KV Compression","created":"2026-04-06","cited_by_count":21,"area":"lr"},{"id":"2503.08879","title":"LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference","created":"2025-03-11","cited_by_count":20,"area":"inference"},{"id":"2512.03324","title":"Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs","created":"2025-12-03","cited_by_count":19,"area":"inference"},{"id":"2508.08438","title":"Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference","created":"2025-08-11","cited_by_count":18,"area":"inference"},{"id":"2503.18893","title":"xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction","created":"2025-03-24","cited_by_count":16,"area":"inference"},{"id":"2506.02475","title":"Comba: Improving Bilinear RNNs with Closed-loop Control","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2510.00231","title":"The Pitfalls of KV Cache Compression","created":"2025-09-30","cited_by_count":15,"area":"inference"},{"id":"2502.11075","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","created":"2025-02-16","cited_by_count":14,"area":null},{"id":"2505.20334","title":"Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query","created":"2025-05-24","cited_by_count":14,"area":"inference"},{"id":"2510.24698","title":"ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking","created":"2025-10-28","cited_by_count":14,"area":"agents"},{"id":"2601.04359","title":"PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache","created":"2026-01-07","cited_by_count":13,"area":"inference"},{"id":"2508.06297","title":"KV Cache Compression for Inference Efficiency in LLMs: A Review","created":"2025-08-08","cited_by_count":12,"area":"inference"},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2605.09649","title":"Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction","created":"2026-05-10","cited_by_count":11,"area":"inference"},{"id":"2502.15075","title":"Quantize What Counts: More for Keys, Less for Values","created":"2025-02-20","cited_by_count":10,"area":"inference"},{"id":"2508.16134","title":"CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing","created":"2025-08-22","cited_by_count":9,"area":"inference"},{"id":"2605.08840","title":"ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing","created":"2026-05-09","cited_by_count":9,"area":"inference"},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2602.03152","title":"FASA: Frequency-aware Sparse Attention","created":"2026-02-03","cited_by_count":8,"area":"inference"},{"id":"2502.04077","title":"AttentionPredictor: Temporal Patterns Matter for KV Cache Compression","created":"2025-02-06","cited_by_count":7,"area":"inference"},{"id":"2506.05410","title":"Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs","created":"2025-06-04","cited_by_count":7,"area":"inference"},{"id":"2508.00904","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2509.04377","title":"PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference","created":"2025-09-04","cited_by_count":7,"area":"inference"},{"id":"2509.15038","title":"Value-Guided KV Compression for LLMs via Approximated CUR Decomposition","created":"2025-09-18","cited_by_count":7,"area":null},{"id":"2512.00504","title":"G-KV: Decoding-Time KV Cache Eviction with Global Attention","created":"2025-11-29","cited_by_count":7,"area":"lr"},{"id":"2601.01204","title":"XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression","created":"2026-01-03","cited_by_count":7,"area":"inference"},{"id":"2604.04722","title":"Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs","created":"2026-04-06","cited_by_count":7,"area":"inference"},{"id":"2504.02800","title":"Survey and Experiments on Mental Disorder Detection via Social Media: From Large Language Models and RAG to Agents","created":"2025-04-03","cited_by_count":6,"area":"agents"},{"id":"2512.03870","title":"Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers","created":"2025-12-03","cited_by_count":6,"area":"inference"},{"id":"2601.17067","title":"A Mechanistic View on Video Generation as World Models: State and Dynamics","created":"2026-01-22","cited_by_count":6,"area":"wm"},{"id":"2606.01563","title":"MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference","created":"2026-06-01","cited_by_count":6,"area":"inference"},{"id":"2606.09916","title":"IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference","created":"2026-06-06","cited_by_count":6,"area":"agents"},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2507.04723","title":"LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2604.19157","title":"SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving","created":"2026-04-21","cited_by_count":5,"area":"inference"},{"id":"2604.25975","title":"Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective","created":"2026-04-28","cited_by_count":5,"area":"lr"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"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":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2503.09579","title":"Cost-Optimal Grouped-Query Attention for Long-Context Modeling","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2505.07239","title":"Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2509.21354","title":"KV-Efficient VLA: A Method to Speed up Vision Language Models with RNN-Gated Chunked KV Cache","created":"2025-09-20","cited_by_count":4,"area":"mllm"},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2512.01953","title":"KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference","created":"2025-12-01","cited_by_count":4,"area":"inference"},{"id":"2512.18337","title":"Towards Efficient Agents: A Co-Design of Inference Architecture and System","created":"2025-12-20","cited_by_count":4,"area":"agents"},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2603.22120","title":"StreamingClaw Technical Report","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2605.05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2605.08317","title":"RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache","created":"2026-05-08","cited_by_count":4,"area":"inference"},{"id":"2607.08057","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","created":"2026-07-09","cited_by_count":4,"area":"inference"},{"id":"2607.09153","title":"KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling","created":"2026-07-10","cited_by_count":4,"area":"lr"},{"id":"2511.16786","title":"Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach","created":"2025-11-20","cited_by_count":3,"area":"mllm"},{"id":"2601.19908","title":"CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference","created":"2025-12-12","cited_by_count":3,"area":"mllm"},{"id":"2602.00250","title":"TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Models","created":"2026-01-30","cited_by_count":3,"area":"diffusion"},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2607.10582","title":"MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference","created":"2026-07-12","cited_by_count":3,"area":"agents"},{"id":"2502.13542","title":"Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2507.13681","title":"LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues","created":"2025-07-18","cited_by_count":2,"area":"inference"},{"id":"2508.19740","title":"Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval","created":"2025-08-27","cited_by_count":2,"area":"inference"},{"id":"2601.06562","title":"Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming","created":"2026-01-10","cited_by_count":2,"area":null},{"id":"2601.11564","title":"Context Discipline and Performance Correlation: Analyzing LLM Performance and Quality Degradation Under Varying Context Lengths","created":"2025-12-25","cited_by_count":2,"area":"moe"},{"id":"2602.08343","title":"ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection","created":"2026-02-09","cited_by_count":2,"area":"inference"},{"id":"2603.13430","title":"Dynamic Sparse Attention: Access Patterns and Architecture","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2604.08304","title":"Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions","created":"2026-04-09","cited_by_count":2,"area":"rag"},{"id":"2605.14037","title":"Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2606.00288","title":"Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2607.01237","title":"KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression","created":"2026-05-01","cited_by_count":2,"area":"lr"},{"id":"2608.04771","title":"Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2609.15160","title":"T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning with Dynamic Routing","created":"2026-09-14","cited_by_count":2,"area":"inference"},{"id":"2502.13251","title":"Neural Attention Search","created":"2025-02-18","cited_by_count":1,"area":"inference"},{"id":"2502.16886","title":"ReFreeKV: Towards Threshold-Free KV Cache Compression","created":"2025-02-24","cited_by_count":1,"area":"inference"},{"id":"2506.12204","title":"Semantic Scheduling for LLM Inference","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2511.02749","title":"Using Span Queries to Optimize for Cache and Attention Locality","created":"2025-11-04","cited_by_count":1,"area":"lr"},{"id":"2512.03608","title":"KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing","created":"2025-12-03","cited_by_count":1,"area":"inference"},{"id":"2602.13665","title":"HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2602.17387","title":"DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.20578","title":"Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems","created":"2026-03-21","cited_by_count":1,"area":"lr"},{"id":"2604.11810","title":"GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.21454","title":"Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2604.26968","title":"Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference","created":"2026-04-19","cited_by_count":1,"area":"inference"},{"id":"2604.27143","title":"Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents","created":"2026-04-29","cited_by_count":1,"area":"agents"},{"id":"2605.06763","title":"Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache","created":"2026-05-07","cited_by_count":1,"area":"inference"},{"id":"2605.16360","title":"ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.00144","title":"BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding","created":"2026-05-29","cited_by_count":1,"area":"inference"},{"id":"2606.09508","title":"From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs","created":"2026-06-08","cited_by_count":1,"area":"inference"},{"id":"2607.06523","title":"DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression","created":"2026-07-07","cited_by_count":1,"area":"inference"},{"id":"2608.09412","title":"KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models","created":"2026-08-10","cited_by_count":1,"area":"inference"},{"id":"2608.30505","title":"Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.39329","title":"PatchKV: Weight-Space Compensation of KV Cache","created":"2026-09-30","cited_by_count":1,"area":"inference"},{"id":"2506.11498","title":"Lag-Relative Sparse Attention In Long Context Training","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2509.02408","title":"Cache Management for Mixture-of-Experts LLMs -- extended version","created":"2025-09-02","cited_by_count":0,"area":"moe"},{"id":"2509.25223","title":"Enhancing Linear Attention with Residual Learning","created":"2025-09-24","cited_by_count":0,"area":null}],"next_cursor":"100"}