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
882 results for “keyword:"attention"” in ICLR 2027. 180 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SharpDraft: Accelerating Long-Context Speculative Decoding with Cardinality-Aware Query Scaling▲3.0k2.33
[PDF]Content-Bounded Phase Consensus: Mitigating Position-Driven Source Preference in Multi-Image Vision-Language Models▲9.2k2.67
[PDF]VestigeKV: Query-Independent Sparse Attention with Certified Recall for NoPE-MLA Caches▼1611.50
[PDF]Depth is Degree: Test-Time-Training Updates Are Polynomial Filters, and Learned Step Sizes Only Choose the Coefficients▼1361.33
[PDF]The Model Knows Where to Look: Distilling Attention Selectors for Long-Context Inference▼5.8k2.33
[PDF]RotateAttention-FP4: A Unified Training-Free and Data-Efficient QAT Framework for Quantized Attention▲11.00
[PDF]Beyond the Attention Lottery: Expressive Power and Topological Complexity via Algebraic Geometry▼1361.33
[PDF]The Saussurean Representation Hypothesis: A Causal Account of Representational Structures in LLMs▼4.3k2.00
[PDF]Eliciting sandbagged LLM capability via structural interventions on attention-head functional networks▼4.3k2.00
[PDF]CoLaDe: Competitive Latent Compression and Lag-Aware Decoding for Time Series Forecasting▼1361.33
Withdrawn or desk rejected (180)
[PDF]FreqBlueprint: Frequency-Bank Guided Dynamic Graph Convolution for Medical Image SegmentationDesk rejected
[PDF]Certified Best-First Sparse Attention: Provable Early Termination via Admissible Block BoundsWithdrawn2.00
[PDF]UniTact: Sequence-Only Unified Antibody–Antigen Interaction Modeling for Contact and Interface PredictionWithdrawn1.00
[PDF]From Frequency to Function: Component-Specific RoPE Extrapolation for Long-Context Language ModelsDesk rejected3.00