{"total":53,"rows":[{"id":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"area":"inference"},{"id":"2412.16117","title":"PruneVid: Visual Token Pruning for Efficient Video Large Language Models","created":"2024-12-20","cited_by_count":67,"area":"inference"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2412.14838","title":"DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs","created":"2024-12-19","cited_by_count":42,"area":"inference"},{"id":"2411.10666","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","created":"2024-11-16","cited_by_count":39,"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":"2507.07990","title":"Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs","created":"2025-07-10","cited_by_count":31,"area":"inference"},{"id":"2502.18779","title":"Towards Optimal Multi-draft Speculative Decoding","created":"2025-02-26","cited_by_count":19,"area":"inference"},{"id":"2412.17483","title":"A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression","created":"2024-12-23","cited_by_count":17,"area":"inference"},{"id":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"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":"2503.16980","title":"VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models","created":"2025-03-21","cited_by_count":12,"area":"inference"},{"id":"2505.24196","title":"CLaSp: In-Context Layer Skip for Self-Speculative Decoding","created":"2025-05-30","cited_by_count":11,"area":"inference"},{"id":"2507.08799","title":"KV Cache Steering for Controlling Frozen LLMs","created":"2025-07-11","cited_by_count":11,"area":"inference"},{"id":"2508.08895","title":"ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs","created":"2025-08-12","cited_by_count":11,"area":"inference"},{"id":"2505.12398","title":"Traversal Verification for Speculative Tree Decoding","created":"2025-05-18","cited_by_count":9,"area":"inference"},{"id":"2602.08005","title":"ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference","created":"2026-02-08","cited_by_count":9,"area":"inference"},{"id":"2503.10714","title":"ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs","created":"2025-03-13","cited_by_count":8,"area":"inference"},{"id":"2602.06502","title":"DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving","created":"2026-02-06","cited_by_count":8,"area":"inference"},{"id":"2409.15395","title":"Parse Trees Guided LLM Prompt Compression","created":"2024-09-23","cited_by_count":6,"area":"inference"},{"id":"2412.09919","title":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens","created":"2024-12-13","cited_by_count":6,"area":"inference"},{"id":"2504.17376","title":"On-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration","created":"2025-04-24","cited_by_count":6,"area":"inference"},{"id":"2411.18424","title":"FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving","created":"2024-11-27","cited_by_count":5,"area":"inference"},{"id":"2511.21669","title":"DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving","created":"2025-11-26","cited_by_count":5,"area":"inference"},{"id":"2603.17946","title":"CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention","created":"2026-03-18","cited_by_count":5,"area":"inference"},{"id":"2408.10497","title":"QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory","created":"2024-08-20","cited_by_count":4,"area":"inference"},{"id":"2502.01025","title":"Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals","created":"2025-02-03","cited_by_count":4,"area":"inference"},{"id":"2502.09921","title":"A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs","created":"2025-02-14","cited_by_count":4,"area":"inference"},{"id":"2505.17138","title":"RAP: Runtime Adaptive Pruning for LLM Inference","created":"2025-05-22","cited_by_count":3,"area":"inference"},{"id":"2509.03136","title":"Adaptive KV-Cache Compression without Manually Setting Budget","created":"2025-09-03","cited_by_count":3,"area":"inference"},{"id":"2605.09463","title":"Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2606.10533","title":"Audio-Visual Exchange-Aware Token Pruning for Efficient Audio-Visual Captioning","created":"2026-06-09","cited_by_count":3,"area":"inference"},{"id":"2605.11774","title":"From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction","created":"2026-05-12","cited_by_count":2,"area":"inference"},{"id":"2412.18106","title":"Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels","created":"2024-12-24","cited_by_count":1,"area":"inference"},{"id":"2507.02620","title":"FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference","created":"2025-07-03","cited_by_count":1,"area":"inference"},{"id":"2509.18344","title":"Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding","created":"2025-09-22","cited_by_count":1,"area":"inference"},{"id":"2509.19368","title":"Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative Decoding","created":"2025-09-19","cited_by_count":1,"area":"inference"},{"id":"2604.03414","title":"KiToke: Kernel-based Interval-aware Token Compression for Video Large Language Models","created":"2026-04-03","cited_by_count":1,"area":"inference"},{"id":"2408.00539","title":"Intermittent Semi-Working Mask: A New Masking Paradigm for LLMs","created":"2024-08-01","cited_by_count":0,"area":"inference"},{"id":"2412.04788","title":"GUIDE: A Global Unified Inference Engine for Deploying Large Language Models in Heterogeneous Environments","created":"2024-12-06","cited_by_count":0,"area":"inference"},{"id":"2503.19950","title":"LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation","created":"2025-03-25","cited_by_count":0,"area":"inference"},{"id":"2604.09547","title":"Tango: Taming Visual Signals for Efficient Video Large Language Models","created":"2026-04-10","cited_by_count":0,"area":"inference"},{"id":"2605.03562","title":"HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization","created":"2026-05-05","cited_by_count":0,"area":"inference"},{"id":"2605.05699","title":"When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon","created":"2026-05-07","cited_by_count":0,"area":"inference"},{"id":"2606.09019","title":"TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech","created":"2026-06-08","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":"2607.02521","title":"Tile-Level Activation Overlap for Efficient LLM Inference","created":"2026-05-05","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":"2607.21985","title":"Unified Static-Dynamic Pruning for Efficient LLM Inference","created":"2026-07-24","cited_by_count":0,"area":"inference"},{"id":"2607.22389","title":"HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding","created":"2026-07-24","cited_by_count":0,"area":"inference"},{"id":"2607.29575","title":"SLIM: Saturation-Aware Lightweight Performance Modeling for LLM Serving","created":"2026-07-31","cited_by_count":0,"area":"inference"},{"id":"2608.30439","title":"Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.09166","title":"X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative Decoding","created":"2026-07-15","cited_by_count":0,"area":"inference"}],"next_cursor":null}