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
619 results for “keyword:"decoding"” in ICLR 2027. 118 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SpecKV: Lossless Speculative Decoding via Dynamic KV Selection for Efficient Inference of Large Vision-Language Models
[PDF]A Patchwise Aggregation Encoder for EEG-to-Image Retrieval: An Analysis of What Image Features Matter▼4.3k2.00
[PDF]SpecSplice: Dynamic Composition of Parametric and Retrieval-based Drafts for Agentic Speculative Decoding▼1.2k3.00
[PDF]StrataSpec: Self-Speculative Decoding with Structured Routes for Efficient LLM Serving▼5.8k2.33
[PDF]E-CALR: Evidential Conflict-Aware Layer-wise Logit Refinement for Factuality-Oriented Decoding▲3.8k2.50
[PDF]Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide▼5.8k2.33
[PDF]Anchor and Follower: Narrowing Valid Answers for Parallel Decoding in Diffusion Language Models▼4.3k2.00
[PDF]What You Think Is What You Plot? A Benchmark for Decoding Visualization Intent from EEG▼4.3k2.00
[PDF]EEG Does Not Spell What You Read: Semantic Neighbourhood Synthesis for Open-Vocabulary EEG-to-Text▲4002.67
[PDF]Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models▼1.2k1.67
[PDF]Matching Only Readouts Tells Incomplete Stories: Temporal Context Shapes Decoding Gains in an Invasive BCI Foundation Model▲6.1k2.00
[PDF]TreePC: Posterior-Consistent and Dependency Aware Decoding for Few-Step Diffusion Language Models▼4.3k2.00
[PDF]Where Does Layer-Skip Fragility Live? A Matched-Harness Decomposition of Training-Free Adaptive Layer Skipping▲11.00
[PDF]Never Sampled, Always Accepted: Commitment Injection Through Top- Verification in Speculative Decoding▲4002.67
Withdrawn or desk rejected (118)
[PDF]NEAR-Bench: Benchmarking Predictive Performance and EEG Input Dependence in EEG-to-Text DecodingWithdrawn2.00
[PDF]What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for SelectionWithdrawn1.67
[PDF]MERIT: MAKING EVERY MODALITY EARN ITS CONTRIBUTION IN MULTIMODAL ATTENTION DECODINGDesk rejected
[PDF]DriftDPO: Mechanism-Guided Preference Optimization for Hallucination Mitigation in Deep-Fusion Vision-Language ModelsWithdrawn1.33
[PDF]Commit Order, Not Commit Rate: Answer Availability and Prefix Preservation in Diffusion Language ModelsWithdrawn1.67
[PDF]ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution ShapingWithdrawn1.67
[PDF]TraceCut: Atomic Action Segmentation and Labeling for Robot Manipulation Videos via Actionability-Aware Hierarchy DecodingWithdrawn1.50