{"total":323,"rows":[{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653,"area":"inference"},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006,"area":"inference"},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880,"area":"inference"},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843,"area":"inference"},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2406.16858","title":"EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees","created":"2024-06-24","cited_by_count":370,"area":"inference"},{"id":"2305.09781","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","created":"2023-05-16","cited_by_count":365,"area":"inference"},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360,"area":null},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331,"area":"inference"},{"id":"2402.02057","title":"Break the Sequential Dependency of LLM Inference Using Lookahead Decoding","created":"2024-02-03","cited_by_count":298,"area":"inference"},{"id":"2401.07851","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","created":"2024-01-15","cited_by_count":269,"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":"2203.16487","title":"Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation","created":"2022-03-30","cited_by_count":171,"area":"inference"},{"id":"2310.08461","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","created":"2023-10-12","cited_by_count":165,"area":"inference"},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2311.03285","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","created":"2023-11-06","cited_by_count":152,"area":null},{"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":"2310.15141","title":"SpecTr: Fast Speculative Decoding via Optimal Transport","created":"2023-10-23","cited_by_count":129,"area":"inference"},{"id":"2305.10427","title":"Accelerating Transformer Inference for Translation via Parallel Decoding","created":"2023-05-17","cited_by_count":124,"area":"inference"},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121,"area":null},{"id":"2402.05109","title":"Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding","created":"2024-02-07","cited_by_count":117,"area":"inference"},{"id":"2310.07177","title":"Online Speculative Decoding","created":"2023-10-11","cited_by_count":113,"area":"inference"},{"id":"2305.16317","title":"Parallel Sampling of Diffusion Models","created":"2023-05-25","cited_by_count":112,"area":"diffusion"},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"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":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","cited_by_count":102,"area":"inference"},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79,"area":null},{"id":"2401.00588","title":"Fairness in Serving Large Language Models","created":"2023-12-31","cited_by_count":78,"area":"inference"},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77,"area":"rag"},{"id":"2402.02082","title":"GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding","created":"2024-02-03","cited_by_count":75,"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":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2410.06916","title":"SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration","created":"2024-10-09","cited_by_count":72,"area":"inference"},{"id":"2406.17276","title":"OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure","created":"2024-06-25","cited_by_count":67,"area":"inference"},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60,"area":null},{"id":"2501.19309","title":"Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment","created":"2025-01-31","cited_by_count":59,"area":"alignment"},{"id":"2504.07891","title":"SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning","created":"2025-04-10","cited_by_count":59,"area":"lr"},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58,"area":null},{"id":"2404.18911","title":"Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting","created":"2024-04-29","cited_by_count":58,"area":"inference"},{"id":"2408.05636","title":"Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion","created":"2024-08-10","cited_by_count":57,"area":"inference"},{"id":"2106.04970","title":"Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding","created":"2021-06-09","cited_by_count":53,"area":"inference"},{"id":"2311.13581","title":"PaSS: Parallel Speculative Sampling","created":"2023-11-22","cited_by_count":49,"area":"inference"},{"id":"2404.00859","title":"Do language models plan ahead for future tokens?","created":"2024-04-01","cited_by_count":49,"area":null},{"id":"2406.02532","title":"SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices","created":"2024-06-04","cited_by_count":46,"area":"inference"},{"id":"2408.07092","title":"Post-Training Sparse Attention with Double Sparsity","created":"2024-08-11","cited_by_count":45,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2501.16975","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","created":"2025-01-28","cited_by_count":44,"area":null},{"id":"2105.03842","title":"FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition","created":"2021-05-09","cited_by_count":43,"area":null},{"id":"2504.13171","title":"Sleep-time Compute: Beyond Inference Scaling at Test-time","created":"2025-04-17","cited_by_count":43,"area":"lr"},{"id":"2110.07515","title":"Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision","created":"2021-10-14","cited_by_count":40,"area":null},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40,"area":null},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2402.11131","title":"Speculative Streaming: Fast LLM Inference without Auxiliary Models","created":"2024-02-16","cited_by_count":38,"area":"inference"},{"id":"2405.19261","title":"Faster Cascades via Speculative Decoding","created":"2024-05-29","cited_by_count":38,"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":"2312.12728","title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","created":"2023-12-20","cited_by_count":37,"area":"inference"},{"id":"2403.09919","title":"Recurrent Drafter for Fast Speculative Decoding in Large Language Models","created":"2024-03-14","cited_by_count":37,"area":"inference"},{"id":"2411.04975","title":"SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications","created":"2024-11-07","cited_by_count":36,"area":"agents"},{"id":"2402.01528","title":"Decoding Speculative Decoding","created":"2024-02-02","cited_by_count":34,"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":"2507.22424","title":"Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance","created":"2025-07-30","cited_by_count":32,"area":"mllm"},{"id":"2401.06706","title":"Multi-Candidate Speculative Decoding","created":"2024-01-12","cited_by_count":31,"area":"inference"},{"id":"2501.05370","title":"Accelerated Diffusion Models via Speculative Sampling","created":"2025-01-09","cited_by_count":31,"area":"diffusion"},{"id":"2403.10444","title":"Block Verification Accelerates Speculative Decoding","created":"2024-03-15","cited_by_count":30,"area":"inference"},{"id":"2411.00841","title":"A Theoretical Perspective for Speculative Decoding Algorithm","created":"2024-10-30","cited_by_count":29,"area":"inference"},{"id":"2502.11517","title":"Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding","created":"2025-02-17","cited_by_count":28,"area":"inference"},{"id":"2603.04791","title":"Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling","created":"2026-03-05","cited_by_count":28,"area":"moe"},{"id":"2503.01342","title":"UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface","created":"2025-03-03","cited_by_count":27,"area":null},{"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":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2402.13720","title":"Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding","created":"2024-02-21","cited_by_count":25,"area":"inference"},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2502.19732","title":"Speculative Decoding and Beyond: An In-Depth Survey of Techniques","created":"2025-02-27","cited_by_count":23,"area":"inference"},{"id":"2509.04185","title":"Set Block Decoding is a Language Model Inference Accelerator","created":"2025-09-04","cited_by_count":23,"area":null},{"id":"2303.07295","title":"Meet in the Middle: A New Pre-training Paradigm","created":"2023-03-13","cited_by_count":22,"area":null},{"id":"2402.11809","title":"Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding","created":"2024-02-19","cited_by_count":22,"area":"inference"},{"id":"2311.17082","title":"DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling","created":"2023-11-28","cited_by_count":20,"area":"diffusion"},{"id":"2401.14021","title":"Accelerating Retrieval-Augmented Language Model Serving with Speculation","created":"2024-01-25","cited_by_count":20,"area":"rag"},{"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":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2509.24007","title":"Sequential Diffusion Language Models","created":"2025-09-28","cited_by_count":19,"area":"diffusion"},{"id":"2205.10350","title":"Lossless Acceleration for Seq2seq Generation with Aggressive Decoding","created":"2022-05-20","cited_by_count":18,"area":null},{"id":"2412.17153","title":"Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching","created":"2024-12-22","cited_by_count":18,"area":"diffusion"},{"id":"2410.03804","title":"Mixture of Attentions For Speculative Decoding","created":"2024-10-04","cited_by_count":17,"area":"inference"},{"id":"2412.01447","title":"PLD+: Accelerating LLM inference by leveraging Language Model Artifacts","created":"2024-12-02","cited_by_count":17,"area":"inference"},{"id":"2605.18810","title":"D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting","created":"2026-05-12","cited_by_count":17,"area":"inference"},{"id":"2405.18628","title":"Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference","created":"2024-05-28","cited_by_count":16,"area":"inference"},{"id":"2410.10786","title":"On Information-Theoretic Measures of Predictive Uncertainty","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2505.10518","title":"Multi-Token Prediction Needs Registers","created":"2025-05-15","cited_by_count":16,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2302.14220","title":"Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation","created":"2023-02-28","cited_by_count":15,"area":null},{"id":"2412.00061","title":"Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration","created":"2024-11-25","cited_by_count":15,"area":"inference"},{"id":"2504.08242","title":"Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices","created":"2025-04-11","cited_by_count":15,"area":"inference"},{"id":"2505.17505","title":"L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models","created":"2025-05-23","cited_by_count":15,"area":null},{"id":"2410.17375","title":"AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration","created":"2024-10-22","cited_by_count":14,"area":"inference"},{"id":"2411.03786","title":"The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation","created":"2024-11-06","cited_by_count":14,"area":"inference"}],"next_cursor":"100"}