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
60 results for “keyword:"attention mechanisms"” in ICLR 2027. 10 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MetaSteer: Context-Conditioned, Non-linear Steering via Attention-Projection Adaptation▲9.2k2.67
[PDF]Beyond the Attention Lottery: Expressive Power and Topological Complexity via Algebraic Geometry▼1361.33
[PDF]RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures▲3.0k2.33
[PDF]LAnoDet: Self-Supervised Lung Anomaly Detection with Transformer-Based Diffusion Models▼1361.33
[PDF]Gating Is Attention: A Plug-and-Play Preference-Gated Dual-Attention Module for Neural Multi-Objective Combinatorial Optimization▼1.2k1.67
[PDF]MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries▼1.2k1.67
[PDF]Receiver-Query Diversity in Graph Transformers: Frozen Interventions Misestimate Adaptive Capacity▼1361.33
[PDF]PRECISION-WEIGHTED ATTENTION: RESTORING UNCERTAINTY TO THE TRANSFORMER FOR SEQUENTIAL RECOMMENDATION▼1.3k1.75
[PDF]MoDANet: A Motif-Aware Distance-Masked Attention Network for Molecular Property Prediction▲1.7k3.33
[PDF]Does Attention Matter in Motor Imagery EEG Decoders? Diagnosing and Repairing Attention Failure▲3.0k2.33
[PDF]Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning▼1.2k1.67
[PDF]How Much Rank Does LoRA Need? Task-Dependent Rank-Error Bounds for Transformer Attention▼1.2k1.67
[PDF]Frequency-Aware Attention: Tokenizer-Induced Self-Information as an Architectural Inductive Bias▼4.3k2.00
[PDF]SPECTRAL SHAPE RESIDUAL: A LIGHTWEIGHT SPECTRAL DIAGNOSTIC FOR ATTENTION WEIGHT MATRICES▼1361.33
Withdrawn or desk rejected (10)
[PDF]UniTact: Sequence-Only Unified Antibody–Antigen Interaction Modeling for Contact and Interface PredictionWithdrawn1.00
[PDF]RAJNI: Importance-Aware, Dispersion-Scheduled Training-Free Token Pruning for Vision TransformersWithdrawn1.67
[PDF]Beyond the Fitted Answer: Causal Dissection and Downstream Consequences of Learned Activation InterventionsWithdrawn1.33
[PDF]Softmax Attention is an Exact Gradient Step: Predictable Finite Responses from RoPE DerivativesWithdrawn2.00