{"total":129,"rows":[{"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":"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":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"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":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"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":"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":"2411.10666","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","created":"2024-11-16","cited_by_count":39,"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":"2504.18583","title":"PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation","created":"2025-04-23","cited_by_count":29,"area":"inference"},{"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":"2410.05589","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","created":"2024-10-08","cited_by_count":22,"area":"inference"},{"id":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","cited_by_count":19,"area":"inference"},{"id":"2410.11305","title":"QSpec: Speculative Decoding with Complementary Quantization Schemes","created":"2024-10-15","cited_by_count":18,"area":"inference"},{"id":"2411.18462","title":"Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation","created":"2024-11-27","cited_by_count":16,"area":"inference"},{"id":"2504.20456","title":"Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding","created":"2025-04-29","cited_by_count":15,"area":"inference"},{"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":"2507.01449","title":"LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation","created":"2025-07-02","cited_by_count":14,"area":"inference"},{"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":"2502.20704","title":"Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff","created":"2025-02-28","cited_by_count":12,"area":"inference"},{"id":"2505.16162","title":"KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization","created":"2025-05-22","cited_by_count":11,"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":"2411.05289","title":"SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding","created":"2024-11-08","cited_by_count":10,"area":"inference"},{"id":"2501.02173","title":"The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit","created":"2025-01-04","cited_by_count":10,"area":"inference"},{"id":"2511.22972","title":"Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match","created":"2025-11-28","cited_by_count":10,"area":"inference"},{"id":"2503.10135","title":"Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding","created":"2025-03-13","cited_by_count":9,"area":"inference"},{"id":"2503.13565","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","created":"2025-03-17","cited_by_count":9,"area":"inference"},{"id":"2503.15921","title":"SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models","created":"2025-03-20","cited_by_count":9,"area":"inference"},{"id":"2504.05598","title":"DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding","created":"2025-04-08","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":"2507.03865","title":"OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference","created":"2025-07-05","cited_by_count":8,"area":"inference"},{"id":"2411.13157","title":"Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding","created":"2024-11-20","cited_by_count":7,"area":"inference"},{"id":"2512.02337","title":"SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification","created":"2025-12-02","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":"2405.20314","title":"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs","created":"2024-05-30","cited_by_count":6,"area":"inference"},{"id":"2506.02006","title":"MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing","created":"2025-05-24","cited_by_count":6,"area":"inference"},{"id":"2602.20217","title":"KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem","created":"2026-02-23","cited_by_count":5,"area":"inference"},{"id":"2410.18952","title":"Dynamic Vocabulary Pruning in Early-Exit LLMs","created":"2024-10-24","cited_by_count":4,"area":"inference"},{"id":"2502.06474","title":"UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths","created":"2025-02-10","cited_by_count":4,"area":"inference"},{"id":"2504.04104","title":"SpecPipe: Accelerating Pipeline Parallelism-based LLM Inference with Speculative Decoding","created":"2025-04-05","cited_by_count":4,"area":"inference"},{"id":"2505.01572","title":"PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding","created":"2025-05-02","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":"2510.26843","title":"CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs","created":"2025-10-30","cited_by_count":4,"area":"inference"},{"id":"2512.23858","title":"Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding","created":"2025-12-29","cited_by_count":4,"area":"inference"},{"id":"2604.07622","title":"DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification","created":"2026-04-08","cited_by_count":4,"area":"inference"},{"id":"2502.02493","title":"EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization","created":"2025-02-04","cited_by_count":3,"area":"inference"},{"id":"2503.17497","title":"You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection","created":"2025-03-21","cited_by_count":3,"area":"inference"},{"id":"2505.17420","title":"DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies","created":"2025-05-23","cited_by_count":3,"area":"inference"},{"id":"2509.23666","title":"Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability","created":"2025-09-28","cited_by_count":3,"area":"inference"},{"id":"2509.24328","title":"Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding","created":"2025-09-29","cited_by_count":3,"area":"inference"},{"id":"2510.01336","title":"HiSpec: Hierarchical Speculative Decoding for LLMs","created":"2025-10-01","cited_by_count":3,"area":"inference"},{"id":"2510.02480","title":"Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting","created":"2025-10-02","cited_by_count":3,"area":"inference"},{"id":"2604.14612","title":"ConfLayers: Adaptive Confidence-based Layer Skipping for Self-Speculative Decoding","created":"2026-04-16","cited_by_count":3,"area":"inference"},{"id":"2607.06763","title":"Trees from Marginals: Autoregressive drafting with factorized priors","created":"2026-07-07","cited_by_count":3,"area":"inference"},{"id":"2505.13254","title":"HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding","created":"2025-05-19","cited_by_count":2,"area":"inference"},{"id":"2505.22757","title":"Pre-Training Curriculum for Multi-Token Prediction in Language Models","created":"2025-05-28","cited_by_count":2,"area":"inference"},{"id":"2506.03566","title":"POSS: Position Specialist Generates Better Draft for Speculative Decoding","created":"2025-06-04","cited_by_count":2,"area":"inference"},{"id":"2511.15898","title":"Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Minimization","created":"2025-11-19","cited_by_count":2,"area":"inference"},{"id":"2512.11280","title":"AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference","created":"2025-12-12","cited_by_count":2,"area":"inference"},{"id":"2512.15705","title":"Dynamic Rebatching for Efficient Early-Exit Inference with DREX","created":"2025-12-17","cited_by_count":2,"area":"inference"},{"id":"2602.01274","title":"PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length","created":"2026-02-01","cited_by_count":2,"area":"inference"},{"id":"2604.02047","title":"Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding","created":"2026-04-02","cited_by_count":2,"area":"inference"},{"id":"2605.16786","title":"Lever: Speculative LLM Inference on Smartphones","created":"2026-05-16","cited_by_count":2,"area":"inference"},{"id":"2605.24793","title":"Beyond the Target: From Imitation to Collaboration in Speculative Decoding","created":"2026-05-24","cited_by_count":2,"area":"inference"},{"id":"2605.29727","title":"Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting","created":"2026-05-28","cited_by_count":2,"area":"inference"},{"id":"2609.09662","title":"PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling","created":"2026-09-09","cited_by_count":2,"area":"inference"},{"id":"2609.17184","title":"LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers","created":"2026-09-15","cited_by_count":2,"area":"inference"},{"id":"2407.01955","title":"S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models","created":"2024-07-02","cited_by_count":1,"area":"inference"},{"id":"2408.11308","title":"Defending against Jailbreak through Early Exit Generation of Large Language Models","created":"2024-08-21","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":"2510.23766","title":"BitSkip: An Empirical Analysis of Quantization and Early Exit Composition in Transformers","created":"2025-10-27","cited_by_count":1,"area":"inference"},{"id":"2510.26527","title":"Polybasic Speculative Decoding Through a Theoretical Perspective","created":"2025-10-30","cited_by_count":1,"area":"inference"},{"id":"2512.20755","title":"Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits","created":"2025-12-23","cited_by_count":1,"area":"inference"},{"id":"2601.23180","title":"TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification","created":"2026-01-30","cited_by_count":1,"area":"inference"},{"id":"2603.01399","title":"Quasar: Quantized Self-Speculative Acceleration for Rapid Inference via Memory-Efficient Verification","created":"2026-03-02","cited_by_count":1,"area":"inference"},{"id":"2603.23701","title":"The Diminishing Returns of Early-Exit Decoding in Modern LLMs","created":"2026-03-24","cited_by_count":1,"area":"inference"},{"id":"2604.12247","title":"SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration","created":"2026-04-14","cited_by_count":1,"area":"inference"},{"id":"2604.18396","title":"River-LLM: Large Language Model Seamless Exit Based on KV Share","created":"2026-04-20","cited_by_count":1,"area":"inference"},{"id":"2604.20503","title":"FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving","created":"2026-04-22","cited_by_count":1,"area":"inference"},{"id":"2605.01106","title":"Component-Aware Self-Speculative Decoding in Hybrid Language Models","created":"2026-05-01","cited_by_count":1,"area":"inference"},{"id":"2607.13093","title":"Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models","created":"2026-07-14","cited_by_count":1,"area":"inference"},{"id":"2608.00531","title":"CURE: Local Uncertainty Repair for Block-Parallel Speculative Decoding","created":"2026-08-01","cited_by_count":1,"area":"inference"},{"id":"2609.17943","title":"ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference","created":"2026-09-16","cited_by_count":1,"area":"inference"},{"id":"2407.21082","title":"Accelerating Large Language Model Inference with Self-Supervised Early Exits","created":"2024-07-30","cited_by_count":0,"area":"inference"},{"id":"2505.08600","title":"Automatic Task Detection and Heterogeneous LLM Speculative Decoding","created":"2025-05-13","cited_by_count":0,"area":"inference"},{"id":"2507.17618","title":"SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token","created":"2025-07-23","cited_by_count":0,"area":"inference"},{"id":"2508.04462","title":"CARD: A Cache-Assisted Parallel Speculative Decoding Framework via Query-and-Correct Paradigm for Accelerating LLM Inference","created":"2025-08-06","cited_by_count":0,"area":"inference"},{"id":"2509.08318","title":"CalexNet: Soft Cascade-Aligned Training and Calibration for Lightweight Early-Exit Branches","created":"2025-09-10","cited_by_count":0,"area":"inference"},{"id":"2510.19705","title":"Fast Inference via Hierarchical Speculative Decoding","created":"2025-10-22","cited_by_count":0,"area":"inference"},{"id":"2512.11718","title":"Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks","created":"2025-12-12","cited_by_count":0,"area":"inference"},{"id":"2602.05499","title":"SDFP: Speculative Decoding with FIT-Pruned Models for Training-Free and Plug-and-Play LLM Acceleration","created":"2026-02-05","cited_by_count":0,"area":"inference"},{"id":"2602.16961","title":"Greedy Multi-Path Block Verification for Faster Decoding in Speculative Sampling","created":"2026-02-18","cited_by_count":0,"area":"inference"},{"id":"2602.16994","title":"Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding","created":"2026-02-19","cited_by_count":0,"area":"inference"},{"id":"2603.09215","title":"SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models","created":"2026-03-10","cited_by_count":0,"area":"inference"},{"id":"2603.21365","title":"TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference","created":"2026-03-22","cited_by_count":0,"area":"inference"},{"id":"2603.27027","title":"TAPS: Task Aware Proposal Distributions for Speculative Sampling","created":"2026-03-27","cited_by_count":0,"area":"inference"},{"id":"2604.13634","title":"Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference","created":"2026-04-15","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}