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
445 results for “keyword:"deep learning"” in ICLR 2027. 84 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MultiUS : Unsupervised Persona Mixture and Norm-Bounded Latent Steering for User Simulation▼1361.33
[PDF]When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay▼4.5k2.25
[PDF]Mind the Gap Between Train and Test Grids: Resolution Collapse in Voxel-Indexed Point Networks Is Mostly a Units Problem▼4.5k2.67
[PDF]Spatio-Temporal Decomposition: A Plug-in Interpretable Front End for Multivariate Time Series Forecasting▼1.3k1.75
[PDF]Learning Canonical Coordinate Systems for Deformable Organs: A Common Coordinate Framework for the Mouse Intestine▼1361.33
[PDF]Reliable Surrogate Modeling of PDEs via Physics-Informed Conformal Prediction on Graph Neural Networks▼1361.33
[PDF]Orbital Specific Exchange: advancing hybrid density functional theory with geometric deep learning▲6.1k2.00
[PDF]E3J: An Efficient and Open-Source Backend for Euclidean Equivariant Operations on GPU and TPU▼4.3k2.00
[PDF]LaCPlow: Geometry-Preserving Partially Latent Flow Matching for Cyclic Peptide Generation▲3972.67
[PDF]A Framework for Analyzing DNN Representation Quality: Dynamics of Interaction Generalizability▼71.25
[PDF]Observation Does Not Imply Control: The Dynamics of Directional Curvature Interventions at the Edge of Stability▼1361.33
[PDF]PHYSINET:PHYSICS-GUIDED WEAKLY-SUPERVISED DEEP LEARNING FOR INTERPRETABLE SEISMIC EVENT CLASSIFICATION AND INVERSE PHYSICAL DISCOVERY▼4.3k2.00
[PDF]Internal Attention: Growing Token Representations Without Growing the FFN or the KV Cache▼1361.33