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
965 results for “keyword:"neural networks"” in ICLR 2027. 200 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Lightweight Explainable Physics-Informed Neural Networks by Learnable Activation Function▲6.1k2.00
[PDF]Cross-Encoder Fairness Degradation in Text-Attributed Graphs via Adversarial Node Injection▲9.2k2.67
[PDF]MTA-SNN: Revitalizing Convolutional Spiking Neural Networks via Multi-Threshold Parallel Neurons and Global-Local Aggregation▼5.8k2.33
[PDF]From Distributions to Stochastic Processes: Neural Approximation of Measure-Valued Maps▼1361.33
[PDF]Causal EpiNets: Scalable Inference for Bounds on the Probability of Positive Individual Treatment Effects▼4.3k2.00
[PDF]MUGAT-KD:A Multimodal-to-Unimodal Knowledge Distillation Framework for Pulmonary Nodule Malignancy Classification▼4.3k2.00
[PDF]DTSA: Dual-Timescale Stability and Adaptation for Robust Offline Reinforcement Learning with Spiking Neural Networks▼5.3k1.33
[PDF]Known-Shortcut Interventions under Mixed Graph Distribution Shifts: A Diagnostic Study▼1.2k1.67
[PDF]Carrying a Length and Counting It Are Different Abilities: A Double Dissociation between Recurrence and Attention in Code-Fence Generation▲6.6k3.33
[PDF]Fed-DREAM: Bridging Fragmented Views in Hybrid Federated Learning via Relational Learning▼4.3k2.00
[PDF]Learn to Collaborate: Autoregressive Diversity-Aware Graph Generation for Multi-Agent Systems▼5.8k2.33
[PDF]Semantic-Guided Structural information Borrowing for Item Cold-Start Recommendation on Graphs▼4.3k2.00
[PDF]A-MFO-Net: Boundary-Conditioned GNN–FNO–GNN Operators for Long-Horizon Room-Scale 3D Thermal-Fluid Simulation▼1.2k1.67
[PDF]Jointly Corrected Parallel Responses in Forecasting Models for Nonlinear Dynamical Systems▼4.3k2.00
[PDF]Thresholds, Not Normalization: A Homeostatic Spiking Layer at Parity Without the Overhead▲6.6k3.33
[PDF]The Amortization Ceiling: Why Learned Policies Do Not Replace Search in Constraint-Satisfaction Graph Generation▼1.2k1.67
[PDF]Resonance Net: Persistent Structured Dynamics for Post-Input and Multimodal Computation▼1.2k1.67
Withdrawn or desk rejected (200)
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]DSS-LVR Flow: A Unified Method for Structural Sparsity in Bayesian Neural NetworksWithdrawn1.00
[PDF]EventGeoPose: Pose-Referenced Event Encoding and Event-Geometry Consistency for Spiking 6D Pose EstimationWithdrawn2.00
[PDF]Graphs are Evidence, Not CircuitsDesk rejected