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
448 results for “keyword:"feature"” in ICLR 2027. 115 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SGD Selects Initialization-Dependent Representation in Overparameterized ReLU Networks▼4.5k2.67
[PDF]How Communication Shapes Convergence and Generalization in Decentralized Training: A Feature Learning Perspective▲3952.67
[PDF]TORE: Token-Wise Taylor Order Selection via Decomposed Residual Error Estimation for Diffusion Acceleration▼13k2.00
[PDF]Prototype Margins and Classifier Decisions: A Geometric Analysis of Deepfake Attribution Robustness▼1.2k1.67
[PDF]PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models▲2843.00
[PDF]When Parameter Bounds Limit Learning: Approximation and Estimation in Mean-Field Neural Networks▼3.7k2.25
[PDF]EndoTME: Physics-Inspired Degradation-Aware Trajectory Memory for Endoscopic Video Enhancement▲5103.00
[PDF]PhasePose: Wavelet Phase Decomposition for Pose Estimation on Low-Resolution Feature Maps▲3.0k2.33
[PDF]Geometry at the Last Mile: Beyond Local Appearance-Only Correspondence Search in Feature Matching▲5.4k3.00
[PDF]PXDepth: Learning Pixel-Space Features for Structure-Preserving Monocular Depth Estimation▲3952.67
[PDF]When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders▼1.2k3.00
[PDF]Separating Free Token Geometry from Raw Feature-Energy Routing: An OAPC Diagnostic Study▼4.3k2.00
[PDF]PLARE: Feature Replacement with a Mixture of Experts for Self-Supervised ECG Representation Learning▼1.2k1.67
[PDF]Quality Signal Is Already There: Training-Free Cross-Domain IQA by Amplifying Latent Quality Direction in Frozen CLIP▲2623.67
[PDF]Bounded Contextual Refinement with Neighborhood Support for Text-Aerial Person Retrieval▲5103.00
[PDF]LociNav: Pose-Indexed Visual Caching and Retrieval for Iterative Object-Goal Navigation▲5103.00
[PDF]THE CONTROL DECIDES THE ANSWER: A MATCHED-OPERATOR NULL FOR EXPLANATION CHANGE UNDER MODEL UPDATES▼1.2k1.67
[PDF]Equivariant Diffusion can have a relatively larger generalization regime than non-equivariant one▼4.3k2.00
Withdrawn or desk rejected (115)
[PDF]Behavior-Based Insider Threat Detection Using Machine Learning: A Comparative Study of Isolation Forest, Random Forest, and XGBoostDesk rejected
[PDF]FreqBlueprint: Frequency-Bank Guided Dynamic Graph Convolution for Medical Image SegmentationDesk rejected
[PDF]Predicting the Predictable: Feature Suppression in Joint-Embedding Predictive ArchitecturesDesk rejected
[PDF]How to Reuse a RepresentationDesk rejected