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619 results for “keyword:"decoding"” in ICLR 2027. 118 withdrawn or desk rejected listed apart.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]EXACT WARM-STATE REUSE FOR HYBRID DIFFUSION LANGUAGE MODELS: CONTRACTS, SPEEDUPS, AND FAILURE BOUNDARIES▲3.0k2.33
[PDF]TapKV: Accelerating Long-Horizon Speculative Decoding with Target-Aware Draft KV Caches Optimization▲4002.67
[PDF]TMOT: Geometric Optimal Transport over Target Representations for Speculative Verification▼1351.33
[PDF]TAKE THE HINT OR PUSH BACK? DECIDING WHEN A VISION-LANGUAGE MODEL SHOULD ACCEPT THE USER’S ANSWER▼1.2k3.00
[PDF]Does Attention Matter in Motor Imagery EEG Decoders? Diagnosing and Repairing Attention Failure▲3.0k2.33
[PDF]From Information to Conditional Contribution: Residual-Informed Sparse Decoding for Traceable Neural Representation Analysis▲4002.67
[PDF]Beyond Full-Context Accuracy: Context-Marginalized Evaluation of Test-Time Structure-Aware Inference in EEG-to-Image Retrieval▼4.5k2.67
[PDF]Sampler Gains Shrink to Noise Under Equal Tuning Budgets: The Winner's Curse in LLM Decoding Evaluation▼1351.33
[PDF]The Parallel-Decoding Score of Masked Diffusion Language Models Is Not a Mutual Information▲13k2.33
[PDF]What The Mask Still Buys: Measuring Which Decoding Constraints Small Language Models Internalize▲11.00
[PDF]CoRD: Conjecture-and-Refutation Decoding for Evidence-Gated Overrides in Collaborative Reasoning▼5.8k2.33
[PDF]DeCoS: Decoding by Contrasting Steered Features Reduces Hallucinations in Large Language Models▼4.5k2.67
[PDF]Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding▲153.33
[PDF]Rethinking Diffusion for Neural Channel Decoding: Aligned Training and Heterogeneous Inference▲5.4k3.00
Withdrawn or desk rejected (118)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