{"total":89,"rows":[{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"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":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160,"area":"inference"},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131,"area":"inference"},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"id":"2401.06104","title":"Transformers are Multi-State RNNs","created":"2024-01-11","cited_by_count":120,"area":"inference"},{"id":"2402.12374","title":"Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding","created":"2024-02-19","cited_by_count":103,"area":"inference"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75,"area":"inference"},{"id":"2503.12491","title":"CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences","created":"2025-03-16","cited_by_count":58,"area":"inference"},{"id":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50,"area":"inference"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2405.16148","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","created":"2024-05-25","cited_by_count":35,"area":"inference"},{"id":"2503.18292","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","created":"2025-03-24","cited_by_count":25,"area":"inference"},{"id":"2406.05317","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","created":"2024-06-08","cited_by_count":19,"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":"2407.12077","title":"GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression","created":"2024-07-16","cited_by_count":18,"area":"inference"},{"id":"2505.17272","title":"Zebra-Llama: Towards Extremely Efficient Hybrid Models","created":"2025-05-22","cited_by_count":18,"area":"inference"},{"id":"2410.00428","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","created":"2024-10-01","cited_by_count":16,"area":"inference"},{"id":"2601.17668","title":"Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction","created":"2026-01-25","cited_by_count":16,"area":"inference"},{"id":"2504.14051","title":"CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction","created":"2025-04-18","cited_by_count":13,"area":"inference"},{"id":"2509.18362","title":"FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction","created":"2025-09-16","cited_by_count":13,"area":"inference"},{"id":"2503.07518","title":"TokenButler: Token Importance is Predictable","created":"2025-03-10","cited_by_count":12,"area":"inference"},{"id":"2409.08464","title":"VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation","created":"2024-09-13","cited_by_count":11,"area":"inference"},{"id":"2407.03157","title":"Let the Code LLM Edit Itself When You Edit the Code","created":"2024-07-03","cited_by_count":10,"area":"inference"},{"id":"2510.05373","title":"KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction","created":"2025-10-06","cited_by_count":10,"area":"inference"},{"id":"2512.05916","title":"KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity","created":"2025-12-05","cited_by_count":10,"area":"inference"},{"id":"2406.07368","title":"When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models","created":"2024-06-11","cited_by_count":9,"area":"inference"},{"id":"2410.23079","title":"BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference","created":"2024-10-30","cited_by_count":9,"area":"inference"},{"id":"2502.12574","title":"HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading","created":"2025-02-18","cited_by_count":9,"area":"inference"},{"id":"2503.16163","title":"SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs","created":"2025-03-20","cited_by_count":9,"area":"inference"},{"id":"2310.08152","title":"Context Compression for Auto-regressive Transformers with Sentinel Tokens","created":"2023-10-12","cited_by_count":8,"area":"inference"},{"id":"2503.24358","title":"SQuat: Subspace-orthogonal KV Cache Quantization","created":"2025-03-31","cited_by_count":7,"area":"inference"},{"id":"2605.05971","title":"Training Transformers for KV Cache Compressibility","created":"2026-05-07","cited_by_count":7,"area":"inference"},{"id":"2412.16187","title":"HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashing","created":"2024-12-13","cited_by_count":6,"area":"inference"},{"id":"2604.20920","title":"Simplified Sparse Attention via Gist Tokens","created":"2026-04-22","cited_by_count":6,"area":"inference"},{"id":"2408.01890","title":"Cross-layer Attention Sharing for Pre-trained Large Language Models","created":"2024-08-04","cited_by_count":5,"area":"inference"},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2503.22196","title":"EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices","created":"2025-03-28","cited_by_count":5,"area":"inference"},{"id":"2508.00367","title":"Representation Shift: Unifying Token Compression with FlashAttention","created":"2025-08-01","cited_by_count":5,"area":"inference"},{"id":"2602.05191","title":"Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"id":"2406.07528","title":"QuickLLaMA: Query-aware Inference Acceleration for Large Language Models","created":"2024-06-11","cited_by_count":4,"area":"inference"},{"id":"2409.15012","title":"Inference-Friendly Models With MixAttention","created":"2024-09-23","cited_by_count":4,"area":"inference"},{"id":"2510.16807","title":"Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads","created":"2025-10-19","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2405.11299","title":"The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving","created":"2024-05-18","cited_by_count":3,"area":"inference"},{"id":"2510.20787","title":"Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction","created":"2025-10-23","cited_by_count":3,"area":"inference"},{"id":"2603.20397","title":"KV Cache Optimization Strategies for Scalable and Efficient LLM Inference","created":"2026-03-20","cited_by_count":3,"area":"inference"},{"id":"2605.19049","title":"KVBuffer: IO-aware Serving for Linear Attention","created":"2026-05-18","cited_by_count":3,"area":"inference"},{"id":"2503.11108","title":"Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding","created":"2025-03-14","cited_by_count":2,"area":"inference"},{"id":"2601.11471","title":"Low-Rank Key Value Attention","created":"2026-01-16","cited_by_count":2,"area":"inference"},{"id":"2602.18196","title":"RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference","created":"2026-02-20","cited_by_count":2,"area":"inference"},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2605.13784","title":"Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers","created":"2026-05-13","cited_by_count":2,"area":"inference"},{"id":"2605.22884","title":"Tensor Cache: Eviction-conditioned Associative Memory for Transformers","created":"2026-05-21","cited_by_count":2,"area":"inference"},{"id":"2608.28444","title":"Sliding-window beats linear attention","created":"2026-08-28","cited_by_count":2,"area":"inference"},{"id":"2609.04434","title":"What Attention Recalls and Recurrence Controls in Hybrid Language Models","created":"2026-09-03","cited_by_count":2,"area":"inference"},{"id":"2403.02352","title":"ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys","created":"2024-03-01","cited_by_count":1,"area":"inference"},{"id":"2505.21077","title":"Efficient Large Language Model Inference with Neural Block Linearization","created":"2025-05-27","cited_by_count":1,"area":"inference"},{"id":"2508.00370","title":"EdgeInfinite-Instruct: Bridging SFT-Based Optimization and NPU-Level Efficiency for Edge Devices","created":"2025-08-01","cited_by_count":1,"area":"inference"},{"id":"2512.09238","title":"Training-free Context-adaptive Attention for Efficient Long Context Modeling","created":"2025-12-10","cited_by_count":1,"area":"inference"},{"id":"2603.10353","title":"S-HPLB: Efficient LLM Attention Serving via Sparsity-Aware Head Parallelism Load Balance","created":"2026-03-11","cited_by_count":1,"area":"inference"},{"id":"2606.09862","title":"Blurry Window Attention","created":"2026-05-31","cited_by_count":1,"area":"inference"},{"id":"2606.16429","title":"Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation","created":"2026-06-15","cited_by_count":1,"area":"inference"},{"id":"2608.15533","title":"DeltaLog: Deferred Materialization of Recurrent States for Linear Attention Decoding","created":"2026-08-16","cited_by_count":1,"area":"inference"},{"id":"2505.20698","title":"Sparsified State-Space Models are Efficient Highway Networks","created":"2025-05-27","cited_by_count":0,"area":"inference"},{"id":"2507.19409","title":"Modality Agnostic Efficient Long Range Encoder","created":"2025-07-25","cited_by_count":0,"area":"inference"},{"id":"2511.04686","title":"Stateful KV Cache Management for LLMs: Balancing Space, Time, Accuracy, and Positional Fidelity","created":"2025-10-23","cited_by_count":0,"area":"inference"},{"id":"2511.19718","title":"Rethinking Vision Transformer Depth via Structural Reparameterization","created":"2025-11-24","cited_by_count":0,"area":"inference"},{"id":"2602.02163","title":"Reg4Pru: Regularisation Through Random Token Routing for Token Pruning","created":"2026-02-02","cited_by_count":0,"area":"inference"},{"id":"2603.04759","title":"Stacked from One: Multi-Scale Self-Injection for Context Window Extension","created":"2026-03-05","cited_by_count":0,"area":"inference"},{"id":"2604.16745","title":"Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals","created":"2026-04-17","cited_by_count":0,"area":"inference"},{"id":"2605.12471","title":"KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference","created":"2026-05-12","cited_by_count":0,"area":"inference"},{"id":"2605.14913","title":"Representative Attention For Vision Transformers","created":"2026-05-14","cited_by_count":0,"area":"inference"},{"id":"2605.20936","title":"DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU","created":"2026-05-20","cited_by_count":0,"area":"inference"},{"id":"2606.18056","title":"ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation","created":"2026-06-16","cited_by_count":0,"area":"inference"},{"id":"2606.21848","title":"Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers","created":"2026-06-20","cited_by_count":0,"area":"inference"},{"id":"2607.11897","title":"Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels","created":"2026-06-12","cited_by_count":0,"area":"inference"},{"id":"2607.19368","title":"Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing","created":"2026-06-12","cited_by_count":0,"area":"inference"},{"id":"2607.24788","title":"GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference","created":"2026-06-26","cited_by_count":0,"area":"inference"},{"id":"2608.21541","title":"Beyond Sparse Weights: When Is Attention Compressible?","created":"2026-08-21","cited_by_count":0,"area":"inference"},{"id":"2609.08189","title":"Do Dynamic Routers Need Memory? HeRo: History-Aware Routing for Efficient LLM Inference","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2610.18654","title":"Kwai Summary Attention V2 Technical Report","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.19210","title":"Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules","created":"2026-10-13","cited_by_count":0,"area":"inference"},{"id":"2610.20503","title":"ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}