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882 results for “keyword:"attention"” in ICLR 2027. 180 withdrawn or desk rejected listed apart.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]Where Does the Recurrence Help? Retrieval-Distance Attribution in Hybrid Sequence Models▼1.2k1.67
[PDF]FORECASTING AS CONDITIONAL TRANSPORT: DOOB- REVERSIBLE GIBBS DYNAMICS ON SPATIO-TEMPORAL GRAPHS▼1.2k1.67
[PDF]QSpar: Co-Designing Sparse Attention and Quantized Weights for Long-Context Self-Speculative Decoding▲5103.00
[PDF]Weight-Dictionary Decomposition: Reading a Transformer's Residual Stream with Its Own Writes▼1361.33
[PDF]Exact Softmax Attention Has the Rectangular Matrix-Multiplication Exponent in Extended Arithmetic Circuits▼1.2k3.00
[PDF]From Rewarding What Models Say to How They Think: Attention Process Reward Model for LLM Reinforcement Learning▼4.3k2.00
[PDF]Bridging Shannon Surprisal and Latent Geometry: A Unified Framework for VLM Storage, Attention Routing, and Data Pruning▼1.2k1.67
[PDF]Attend to Vision When It Matters: Visual Dependency-Aware Attention Rebalancing for Large Vision-Language Models▼5.8k2.33
[PDF]Resolving Spatial and Semantic Conflicts in Multi-LoRA Composition via Softmax Routing and Cross-Adapter Attention Conditioning▼1.2k1.67
[PDF]SFA: A Statistical Physics-Inspired Diffusion Transformer for Efficient and High-Quality Image Generation▲3.0k2.33
[PDF]ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory▼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Withdrawn or desk rejected (180)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