{"total":181,"rows":[{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653,"area":"inference"},{"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":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474,"area":"inference"},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348,"area":"inference"},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310,"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":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203,"area":"inference"},{"id":"2403.19708","title":"Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention","created":"2024-03-23","cited_by_count":163,"area":"inference"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2311.08252","title":"REST: Retrieval-Based Speculative Decoding","created":"2023-11-14","cited_by_count":150,"area":"inference"},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115,"area":"inference"},{"id":"2203.07259","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","created":"2022-03-14","cited_by_count":115,"area":"inference"},{"id":"2210.03162","title":"Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models","created":"2022-10-06","cited_by_count":97,"area":"inference"},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2307.02628","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","created":"2023-07-05","cited_by_count":89,"area":"inference"},{"id":"2305.13144","title":"Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline","created":"2023-05-22","cited_by_count":86,"area":"inference"},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2412.01827","title":"RandAR: Decoder-only Autoregressive Visual Generation in Random Orders","created":"2024-12-02","cited_by_count":83,"area":"inference"},{"id":"2405.19715","title":"SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths","created":"2024-05-30","cited_by_count":75,"area":"inference"},{"id":"2406.12335","title":"Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters","created":"2024-06-18","cited_by_count":73,"area":"inference"},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69,"area":"inference"},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"id":"2404.08509","title":"Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction","created":"2024-04-12","cited_by_count":66,"area":"inference"},{"id":"2401.03868","title":"FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs","created":"2024-01-08","cited_by_count":64,"area":"inference"},{"id":"2305.17328","title":"Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers","created":"2023-05-27","cited_by_count":62,"area":"inference"},{"id":"2401.15569","title":"Efficient Tuning and Inference for Large Language Models on Textual Graphs","created":"2024-01-28","cited_by_count":54,"area":"inference"},{"id":"2403.02991","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","created":"2024-03-05","cited_by_count":54,"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":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50,"area":"inference"},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46,"area":"inference"},{"id":"2402.13516","title":"ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models","created":"2024-02-21","cited_by_count":45,"area":"inference"},{"id":"2203.13240","title":"Token Dropping for Efficient BERT Pretraining","created":"2022-03-24","cited_by_count":42,"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":"2105.11618","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","created":"2021-05-25","cited_by_count":40,"area":"inference"},{"id":"2310.01812","title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","created":"2023-10-03","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":"2503.23367","title":"FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning","created":"2025-03-30","cited_by_count":34,"area":"inference"},{"id":"2203.01670","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","created":"2022-03-03","cited_by_count":32,"area":"inference"},{"id":"2406.02657","title":"Block Transformer: Global-to-Local Language Modeling for Fast Inference","created":"2024-06-04","cited_by_count":32,"area":"inference"},{"id":"2105.13878","title":"Accelerating BERT Inference for Sequence Labeling via Early-Exit","created":"2021-05-28","cited_by_count":29,"area":"inference"},{"id":"2410.20771","title":"MrT5: Dynamic Token Merging for Efficient Byte-level Language Models","created":"2024-10-28","cited_by_count":28,"area":"inference"},{"id":"2408.08147","title":"P/D-Serve: Serving Disaggregated Large Language Model at Scale","created":"2024-08-15","cited_by_count":27,"area":"inference"},{"id":"2410.17897","title":"Value Residual Learning","created":"2024-10-23","cited_by_count":27,"area":"inference"},{"id":"2509.25188","title":"Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding","created":"2025-09-29","cited_by_count":27,"area":"inference"},{"id":"2503.04992","title":"Wanda++: Pruning Large Language Models via Regional Gradients","created":"2025-03-06","cited_by_count":26,"area":"inference"},{"id":"2410.23782","title":"Video Token Merging for Long-form Video Understanding","created":"2024-10-31","cited_by_count":23,"area":"inference"},{"id":"2502.07578","title":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","created":"2025-02-11","cited_by_count":22,"area":"inference"},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2503.10568","title":"Autoregressive Image Generation with Randomized Parallel Decoding","created":"2025-03-13","cited_by_count":20,"area":"inference"},{"id":"2408.05235","title":"SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving","created":"2024-08-05","cited_by_count":19,"area":"inference"},{"id":"2602.08024","title":"FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging","created":"2026-02-08","cited_by_count":18,"area":"inference"},{"id":"2111.00230","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","created":"2021-10-30","cited_by_count":16,"area":"inference"},{"id":"2112.06540","title":"A Study on Token Pruning for ColBERT","created":"2021-12-13","cited_by_count":15,"area":"inference"},{"id":"2312.05385","title":"Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving","created":"2023-12-08","cited_by_count":15,"area":"inference"},{"id":"2403.01136","title":"LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization","created":"2024-03-02","cited_by_count":15,"area":"inference"},{"id":"2107.00175","title":"Elbert: Fast Albert with Confidence-Window Based Early Exit","created":"2021-07-01","cited_by_count":14,"area":"inference"},{"id":"2305.12228","title":"Dynamic Transformers Provide a False Sense of Efficiency","created":"2023-05-20","cited_by_count":14,"area":"inference"},{"id":"2310.06927","title":"Sparse Fine-tuning for Inference Acceleration of Large Language Models","created":"2023-10-10","cited_by_count":14,"area":"inference"},{"id":"2409.17372","title":"Search for Efficient Large Language Models","created":"2024-09-25","cited_by_count":14,"area":"inference"},{"id":"2309.09195","title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","created":"2023-09-17","cited_by_count":13,"area":"inference"},{"id":"2312.11882","title":"ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference","created":"2023-12-19","cited_by_count":13,"area":"inference"},{"id":"2410.17175","title":"Remote Timing Attacks on Efficient Language Model Inference","created":"2024-10-22","cited_by_count":13,"area":"inference"},{"id":"2404.15420","title":"XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference","created":"2024-04-23","cited_by_count":12,"area":"inference"},{"id":"2405.15039","title":"CEEBERT: Cross-Domain Inference in Early Exit BERT","created":"2024-05-23","cited_by_count":12,"area":"inference"},{"id":"2305.15273","title":"Revisiting Token Dropping Strategy in Efficient BERT Pretraining","created":"2023-05-24","cited_by_count":11,"area":"inference"},{"id":"2507.01957","title":"Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation","created":"2025-07-02","cited_by_count":10,"area":"inference"},{"id":"2301.07099","title":"Adaptive Deep Neural Network Inference Optimization with EENet","created":"2023-01-15","cited_by_count":9,"area":"inference"},{"id":"2303.09266","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","created":"2023-03-16","cited_by_count":9,"area":"inference"},{"id":"2403.08312","title":"StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses","created":"2024-03-13","cited_by_count":9,"area":"inference"},{"id":"2409.14364","title":"Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models","created":"2024-09-22","cited_by_count":9,"area":"inference"},{"id":"2505.09142","title":"ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor","created":"2025-05-14","cited_by_count":9,"area":"inference"},{"id":"2507.13032","title":"Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation","created":"2025-07-17","cited_by_count":9,"area":"inference"},{"id":"2510.11938","title":"FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters","created":"2025-10-13","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":"2407.20485","title":"A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder","created":"2024-07-30","cited_by_count":8,"area":"inference"},{"id":"2503.06594","title":"Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation","created":"2025-03-09","cited_by_count":8,"area":"inference"},{"id":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2505.00019","title":"An Empirical Study on Prompt Compression for Large Language Models","created":"2025-04-24","cited_by_count":8,"area":"inference"},{"id":"2311.08623","title":"DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models","created":"2023-11-15","cited_by_count":7,"area":"inference"},{"id":"2403.14919","title":"Hierarchical Skip Decoding for Efficient Autoregressive Text Generation","created":"2024-03-22","cited_by_count":7,"area":"inference"},{"id":"2405.14371","title":"EdgeShard: Efficient LLM Inference via Collaborative Edge Computing","created":"2024-05-23","cited_by_count":7,"area":"inference"},{"id":"2411.01076","title":"When Speculation Spills Secrets: Side Channels via Speculative Decoding In LLMs","created":"2024-11-01","cited_by_count":7,"area":"inference"},{"id":"2502.10659","title":"Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGA","created":"2025-02-15","cited_by_count":7,"area":"inference"},{"id":"2510.20064","title":"Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs","created":"2025-10-22","cited_by_count":7,"area":"inference"},{"id":"2204.03276","title":"PALBERT: Teaching ALBERT to Ponder","created":"2022-04-07","cited_by_count":6,"area":"inference"},{"id":"2306.14393","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","created":"2023-06-26","cited_by_count":6,"area":"inference"},{"id":"2502.00745","title":"BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts","created":"2025-02-02","cited_by_count":6,"area":"inference"},{"id":"2504.00030","title":"Token-Driven GammaTune: Adaptive Calibration for Enhanced Speculative Decoding","created":"2025-03-28","cited_by_count":6,"area":"inference"},{"id":"2511.20973","title":"Towards Audio Token Compression in Large Audio Language Models","created":"2025-11-26","cited_by_count":6,"area":"inference"},{"id":"2602.13836","title":"Speculative Decoding with a Speculative Vocabulary","created":"2026-02-14","cited_by_count":6,"area":"inference"},{"id":"2606.17034","title":"KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing","created":"2026-06-15","cited_by_count":6,"area":"inference"},{"id":"2303.03800","title":"Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding","created":"2023-03-07","cited_by_count":5,"area":"inference"},{"id":"2306.02307","title":"Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings","created":"2023-06-04","cited_by_count":5,"area":"inference"},{"id":"2405.13019","title":"A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models","created":"2024-05-15","cited_by_count":5,"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":"2410.04424","title":"DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs","created":"2024-10-06","cited_by_count":5,"area":"inference"},{"id":"2503.07956","title":"EFPC: Towards Efficient and Flexible Prompt Compression","created":"2025-03-11","cited_by_count":5,"area":"inference"},{"id":"2503.11816","title":"Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques","created":"2025-03-14","cited_by_count":5,"area":"inference"}],"next_cursor":"100"}