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
33 results for “keyword:"efficient attention"” in ICLR 2027. 2 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]AVQ-Attention-2: Adaptive Vector-Quantized Attention with Exact Local Blocks and Linear-Cost Training▲9.2k2.67
[PDF]MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries▼1.2k1.67
[PDF]The Context of Theseus: Learning Selective Discrete Recurrence in Autoregressive Transformers▲6.1k2.00
[PDF]Efficient Zero-shot Spatio-Temporal Forecasting via Multi-scale Expert Distilled Mixed Hashing Attention▼4.3k2.00
[PDF]AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers▲5103.00
[PDF]Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores▲153.33
[PDF]Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration▲4012.67
[PDF]HiRouter: Efficient Maximum Inner Product Search for Top- Attention via Hierarchical Routers▼11k1.75