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195 results for “keyword:"speculative decoding"” in ICLR 2027. 31 withdrawn or desk rejected listed apart.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]RIVET: Ragged Inference with Variable-Granularity Execution for Token-Tree Verification in Speculative Decoding▼1.2k1.67
[PDF]AOSR: Asynchronous On-Policy Speculative Rollout for Efficient Distillation of Autoregressive Image Generators▲5.4k3.00
[PDF]Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion–AR Self-Speculation Frontier▼5.8k2.33
[PDF]Shallow Queries, Mature Values: Depth-Asynchronous Self-Speculation for Looped Transformers▲9.2k2.67
[PDF]DSpark-OPD: Acceptance-Aligned On-Policy Distillation for Semi-Autoregressive Speculative Drafting▼1.2k1.67
[PDF]QSpar: Co-Designing Sparse Attention and Quantized Weights for Long-Context Self-Speculative Decoding▲5103.00
[PDF]TraSURE: Exploiting Cross-trajectory Recurrence to Accelerate Information-seeking RL Rollouts over Shared Corpora▼5.8k2.33
[PDF]AdaptSpec: Input- and Step-Adaptive Tree-Based Speculative Decoding to Accelerate LLM Inference▼1.2k1.67
[PDF]CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration▼5.1k2.60
[PDF]Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds▲4002.67
[PDF]Speculating on the Past: Lossless Reuse of Stale KV Caches via Self-Speculative Verification▼4.3k2.00
[PDF]JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting▲9.2k2.67
[PDF]LoadMatch: Balancing Memory and Compute Loads in Quantized Models using Speculative Decoding▼4.3k2.00
[PDF]Speculative Pipeline Decoding: Higher-Accuracy Drafting with Hidden Latency via Pipeline Parallelism▲4002.67
Withdrawn or desk rejected (31)
[PDF]ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution ShapingWithdrawn1.67
[PDF]SQB-Spec: Accelerating Large Multimodal Models through Task-Specific Speculative DecodingDesk rejected
[PDF]Separating marginal error from recoverable dependence in parallel-head speculative decoding for large language modelsDesk rejected2.33
[PDF]VerifyLocal: Learning Expert-Residency-Conditioned Proposals for Exact MoE Speculative DecodingWithdrawn2.00
[PDF]Confidence-Adaptive Permutation-Tree Self Speculative Decoding for Diffusion Large Language ModelsWithdrawn1.67
[PDF]Beyond the Tip of the Iceberg: Depth-Aware Top- Margin Distillation for Diffusion Speculative DecodingWithdrawn1.67
[PDF]Grammar Reachability for Lossless LM-Head Compression and Deterministic Token Injection in Structured GenerationWithdrawn1.33
[PDF]REASONING-AWARE SPECULATIVE DECODING FOR EFFICIENT VISION-LANGUAGE-ACTION MODELS IN AUTONOMOUS DRIVINGWithdrawn