{"total":165,"rows":[{"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":"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":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2604.00626","title":"A Survey of On-Policy Distillation for Large Language Models","created":"2026-04-01","cited_by_count":163,"area":"distill"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2402.05109","title":"Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding","created":"2024-02-07","cited_by_count":117,"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":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2408.11850","title":"PEARL: Parallel Speculative Decoding with Adaptive Draft Length","created":"2024-08-13","cited_by_count":85,"area":"inference"},{"id":"2402.10631","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","created":"2024-02-16","cited_by_count":84,"area":"distill"},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84,"area":null},{"id":"2312.11462","title":"Cascade Speculative Drafting for Even Faster LLM Inference","created":"2023-12-18","cited_by_count":83,"area":"inference"},{"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":"2403.00835","title":"CLLMs: Consistency Large Language Models","created":"2024-02-28","cited_by_count":72,"area":"inference"},{"id":"2408.15766","title":"Learning Harmonized Representations for Speculative Sampling","created":"2024-08-28","cited_by_count":72,"area":"inference"},{"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":"2501.19309","title":"Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment","created":"2025-01-31","cited_by_count":59,"area":"alignment"},{"id":"2404.18911","title":"Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting","created":"2024-04-29","cited_by_count":58,"area":"inference"},{"id":"2410.03355","title":"LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding","created":"2024-10-04","cited_by_count":47,"area":"diffusion"},{"id":"2507.11851","title":"Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential","created":"2025-07-16","cited_by_count":47,"area":null},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"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":"2403.09919","title":"Recurrent Drafter for Fast Speculative Decoding in Large Language Models","created":"2024-03-14","cited_by_count":37,"area":"inference"},{"id":"2406.14066","title":"TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput","created":"2024-06-20","cited_by_count":37,"area":"inference"},{"id":"2401.06706","title":"Multi-Candidate Speculative Decoding","created":"2024-01-12","cited_by_count":31,"area":"inference"},{"id":"2403.10444","title":"Block Verification Accelerates Speculative Decoding","created":"2024-03-15","cited_by_count":30,"area":"inference"},{"id":"2508.08712","title":"A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models","created":"2025-08-12","cited_by_count":30,"area":"diffusion"},{"id":"2411.00841","title":"A Theoretical Perspective for Speculative Decoding Algorithm","created":"2024-10-30","cited_by_count":29,"area":"inference"},{"id":"2402.14160","title":"Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement","created":"2024-02-21","cited_by_count":27,"area":"inference"},{"id":"2511.00606","title":"SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding","created":"2025-11-01","cited_by_count":26,"area":"diffusion"},{"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":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","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":"2403.00858","title":"Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs","created":"2024-02-29","cited_by_count":22,"area":"inference"},{"id":"2410.05589","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","created":"2024-10-08","cited_by_count":22,"area":"inference"},{"id":"2510.24021","title":"SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs","created":"2025-10-28","cited_by_count":22,"area":"distill"},{"id":"2502.14856","title":"FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling","created":"2025-02-20","cited_by_count":20,"area":"inference"},{"id":"2505.15141","title":"BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms","created":"2025-05-21","cited_by_count":20,"area":"inference"},{"id":"2411.11925","title":"Continuous Speculative Decoding for Autoregressive Image Generation","created":"2024-11-18","cited_by_count":19,"area":"inference"},{"id":"2412.12687","title":"Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models","created":"2024-12-17","cited_by_count":19,"area":null},{"id":"2502.18779","title":"Towards Optimal Multi-draft Speculative Decoding","created":"2025-02-26","cited_by_count":19,"area":"inference"},{"id":"2510.26475","title":"ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems","created":"2025-10-30","cited_by_count":18,"area":"lr"},{"id":"2602.23881","title":"LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding","created":"2026-02-27","cited_by_count":18,"area":"inference"},{"id":"2410.03804","title":"Mixture of Attentions For Speculative Decoding","created":"2024-10-04","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":"2502.11018","title":"GRIFFIN: Effective Token Alignment for Faster Speculative Decoding","created":"2025-02-16","cited_by_count":16,"area":"inference"},{"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":"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":"2606.18394","title":"JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting","created":"2026-06-16","cited_by_count":15,"area":"inference"},{"id":"2410.17375","title":"AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration","created":"2024-10-22","cited_by_count":14,"area":"inference"},{"id":"2505.19201","title":"DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding","created":"2025-05-25","cited_by_count":14,"area":"mllm"},{"id":"2501.12689","title":"IC-Cache: Efficient Large Language Model Serving via In-context Caching","created":"2025-01-22","cited_by_count":13,"area":null},{"id":"2406.16758","title":"Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters","created":"2024-06-24","cited_by_count":12,"area":"inference"},{"id":"2502.01662","title":"Fast Large Language Model Collaborative Decoding via Speculation","created":"2025-02-01","cited_by_count":12,"area":null},{"id":"2509.01920","title":"Dynamic Speculative Agent Planning","created":"2025-09-02","cited_by_count":12,"area":"agents"},{"id":"2604.09603","title":"ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios","created":"2026-03-10","cited_by_count":12,"area":"inference"},{"id":"2408.12168","title":"FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation","created":"2024-08-22","cited_by_count":11,"area":null},{"id":"2410.05165","title":"Efficient Inference for Large Language Model-based Generative Recommendation","created":"2024-10-07","cited_by_count":11,"area":null},{"id":"2410.18234","title":"Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits","created":"2024-10-23","cited_by_count":11,"area":"inference"},{"id":"2506.22694","title":"VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs","created":"2025-06-28","cited_by_count":11,"area":"inference"},{"id":"2511.14102","title":"MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts","created":"2025-11-18","cited_by_count":11,"area":"moe"},{"id":"2402.08644","title":"Tandem Transformers for Inference Efficient LLMs","created":"2024-02-13","cited_by_count":10,"area":"inference"},{"id":"2405.00263","title":"Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge","created":"2024-05-01","cited_by_count":10,"area":"inference"},{"id":"2405.14105","title":"Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference","created":"2024-05-23","cited_by_count":9,"area":"inference"},{"id":"2410.20418","title":"Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models","created":"2024-10-27","cited_by_count":8,"area":"inference"},{"id":"2502.08020","title":"Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding","created":"2025-02-11","cited_by_count":8,"area":null},{"id":"2504.00623","title":"Efficient Construction of Model Family through Progressive Training Using Model Expansion","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2510.19779","title":"AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders","created":"2025-10-22","cited_by_count":8,"area":"inference"},{"id":"2605.08632","title":"PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding","created":"2026-05-09","cited_by_count":8,"area":"inference"},{"id":"2404.14897","title":"Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models","created":"2024-04-23","cited_by_count":7,"area":"inference"},{"id":"2409.01366","title":"CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification","created":"2024-09-02","cited_by_count":7,"area":null},{"id":"2602.06019","title":"Multi-Token Prediction via Self-Distillation","created":"2026-02-05","cited_by_count":7,"area":"inference"},{"id":"2602.07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","created":"2026-02-06","cited_by_count":7,"area":"inference"},{"id":"2402.15758","title":"Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens","created":"2024-02-24","cited_by_count":6,"area":"inference"},{"id":"2408.08146","title":"KOALA: Enhancing Speculative Decoding for LLM via Multi-Layer Draft Heads with Adversarial Learning","created":"2024-08-15","cited_by_count":6,"area":"inference"},{"id":"2411.11055","title":"FastDraft: How to Train Your Draft","created":"2024-11-17","cited_by_count":6,"area":"inference"},{"id":"2502.03460","title":"Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2502.08923","title":"CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality","created":"2025-02-13","cited_by_count":6,"area":"inference"},{"id":"2505.18629","title":"Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"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":"2408.00264","title":"Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding","created":"2024-08-01","cited_by_count":5,"area":"inference"},{"id":"2505.11788","title":"Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2608.30135","title":"Verification-Aware Training for Speculative Decoding","created":"2026-08-31","cited_by_count":5,"area":"inference"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2502.17717","title":"Knowledge Distillation with Training Wheels","created":"2025-02-24","cited_by_count":4,"area":"distill"},{"id":"2505.07858","title":"Scaling Laws for Speculative Decoding","created":"2025-05-08","cited_by_count":4,"area":"lr"},{"id":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2506.05632","title":"List-Level Distribution Coupling with Applications to Speculative Decoding and Lossy Compression","created":"2025-06-05","cited_by_count":4,"area":"inference"},{"id":"2507.02659","title":"OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding","created":"2025-07-03","cited_by_count":4,"area":"inference"},{"id":"2510.02329","title":"SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification","created":"2025-09-26","cited_by_count":4,"area":"inference"},{"id":"2510.05421","title":"Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding","created":"2025-10-06","cited_by_count":4,"area":"inference"}],"next_cursor":"100"}