{"total":16,"rows":[{"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":"2505.12398","title":"Traversal Verification for Speculative Tree Decoding","created":"2025-05-18","cited_by_count":9,"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":"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":"2510.02329","title":"SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification","created":"2025-09-26","cited_by_count":4,"area":"inference"},{"id":"2601.05724","title":"Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding","created":"2026-01-09","cited_by_count":4,"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":"2604.25925","title":"SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding","created":"2026-04-01","cited_by_count":2,"area":"inference"},{"id":"2510.26527","title":"Polybasic Speculative Decoding Through a Theoretical Perspective","created":"2025-10-30","cited_by_count":1,"area":"inference"},{"id":"2605.04543","title":"UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding","created":"2026-05-06","cited_by_count":1,"area":"inference"},{"id":"2608.24411","title":"ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping","created":"2026-08-25","cited_by_count":1,"area":"inference"},{"id":"2609.21827","title":"RheoSampling: Resolving the One-Hot Dilemma in Stochastic Dynamic-Tree Speculative Decoding","created":"2026-09-18","cited_by_count":1,"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":"2609.33652","title":"Tsubame: Tree Replay for Diffusion-Based Speculative Decoding","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2610.00321","title":"CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters","created":"2026-09-29","cited_by_count":0,"area":"inference"}],"next_cursor":null}