NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
195 results for “keyword:"speculative decoding"” in ICLR 2027. 31 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RANA: Accelerating Multi-Turn Agentic Reinforcement Learning with Speculative Decoding▼4.3k2.00
[PDF]Frequencies Rank, Probabilities Allocate: Calibrated Draft Trees for Drafter-Free Speculative Decoding▲4012.67
[PDF]StreamBank: Unified Generation–Memory Inference for Efficient Streaming Video Understanding▼5.8k2.33
[PDF]LatentSpec: Two-Stage Thinker–Drafter Parallel Drafting with Shared Latent Reasoning for Speculative Decoding▲9.2k2.67
[PDF]The Generative Gap Between Speculative Drafter and Continuous Diffusion Language Model▼4.3k2.00
[PDF]When to Trust the Past: Reliability-Calibrated Draft-Tree Orchestration for Speculative Decoding▲4012.67
[PDF]SharpDraft: Accelerating Long-Context Speculative Decoding with Cardinality-Aware Query Scaling▲3.0k2.33
[PDF]Draft Calibration for Speculative Decoding: Accelerating LLM Serving by Matching Draft and Target Distributions▲5103.00
[PDF]DStreamer: Acceptance-Aligned Diffusion Streaming for High-Throughput Serving and Online RLVR▲4012.67
[PDF]Dispersed Any-Order Speculative Decoding for Exact Parallel Autoregressive Image Generation▲4.6k3.00
[PDF]Does a Grammar-Constrained Speculative Verifier Sample the Conditional Law? Fidelity Bounds, Numerical Paths and Exact Acquisition▼4.3k2.00
[PDF]ReDraft: Your Verifier Is Secretly a Depth Supervisor for Recurrent Speculative Decoding▲5103.00
[PDF]Fork and Regenerate: MTP-Guided Early Forking and Suffix Regeneration for Block Diffusion Speculative Decoding▲3.0k2.33
[PDF]Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding▼4.3k2.00
[PDF]SPEAR: Exact Self-Speculative Sampling from the Autoregressive-Order Policy of Diffusion Language Models▲3.0k2.33
[PDF]A RIGOR-MATCHED AUDIT OF PERIODIC-STEP LAYER SKIPPING FOR EFFICIENT LLM INFERENCE: CONFLAYERS VERSUS SWIFT, WITH A SUPPLEMENTAL ANALYSIS OF TRAINED ROUTING ALTERNATIVES▲11.00
Withdrawn or desk rejected (31)
[PDF]SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language ModelsDesk rejected2.33
[PDF]Lossless, Yet Not Identical: Execution-Level Numerical Bifurcations in Speculative DecodingWithdrawn1.33