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
1,103 results for “keyword:"transform"” in ICLR 2027. 230 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LLM-as-its-judge: A compute paradigm for self-aware and self-directing reasoning machines▼4.3k2.00
[PDF]Mimir: A Sub-2B Hierarchical Reasoning Model Trained on Permissible Data Punches Above Its Weight Class▼1.2k1.67
[PDF]Bootstrap Your Own Noise: Denoising and Latent Prediction Cooperate Only When Noise Is Informative and Alignment Is Gated▼1.2k3.00
[PDF]More Than Correct Answers: Testing, Tracing, and Predicting Multi-Hop Execution in Transformers▲6.1k2.00
[PDF]RAC-Net: Patch-based Multivariate Time Series Forecasting via Codebook Routing and Small Language Model Distillation▼5.8k2.33
[PDF]Learning What Structure to Preserve for Source-Faithful Generative Image Super-Resolution▼1.2k1.67
[PDF]BiXformer: A Bidirectional Cross Attention Transformer for Disentangling Inter-Regional Neural Dynamics▲5.4k3.00
[PDF]Persistence Positional Encoding: A Minimal Transformer Recipe for Persistence Diagrams▼4.5k2.25
[PDF]MoDANet: A Motif-Aware Distance-Masked Attention Network for Molecular Property Prediction▲1.7k3.33
[PDF]When Exact Loops Beat Shortcuts: Deep-Target Approximation Is Not Recurrent-Depth Acceleration▲6.1k2.00
[PDF]Iterate, Don't Stack: Grounded Recursive Transformers for Generalizable Novel View Synthesis▲5.4k3.00
[PDF]A model-agnostic scaling rule behind the critical inverse temperature in softmax self-attention▲2843.00
[PDF]When Amortized Posteriors Become Priors: One-Shot Accuracy Does Not Certify Recursive Reuse▼1.2k1.67
[PDF]Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does▼4.3k2.00
Withdrawn or desk rejected (230)
[PDF]Caustic Spectroscopy: Identifiability and Acquisition Limits of Topological Event TimingWithdrawn2.00
[PDF]Decoupling Temporal Action Ownership and Actor Geometry for Spatio-Temporal Action LocalizationWithdrawn1.33
[PDF]Activation Density in Transformer Feed-Forward Networks Is Set by the Nonlinearity, Not the WidthWithdrawn2.00