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
1,550 results for “keyword:"network"” in ICLR 2027. 326 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]TaylorSSM: Dependence-Preserving Robustness Certification for Selective State-Space Models▲3.0k2.33
[PDF]Accelerating Global optimisation with Piecewise-Linear Kolmogorov-Arnold Network Surrogates▼5.8k2.33
[PDF]Learning to Decompose and Act: Landmark-Based Manager–Worker Policies for Generalized Planning at Scale▲3942.67
[PDF]ConDenFormer: A Conductance-Inspired Spiking Transformer with Dendritic Memory and Adaptive Neuronal Dynamics▼5.8k2.33
[PDF]A Spiking Neural Network Learning Rule Integrating Multi-scale Eligibility Traces and Steady-state Adaptation▼5.8k2.33
[PDF]Stealth Still Leaves Traces: Exposing and Reducing Trigger Footprints in Graph Backdoor Attacks▼4.3k2.00
[PDF]Spatio-Temporal Margin Regularization for Mitigating Temporal Error Accumulation in Spiking Neural Networks▼4.3k2.00
[PDF]KU-GAD: Rethinking Semi-Supervised Graph Anomaly Detection with Known–Unlabeled Discrimination▲5103.00
[PDF]Functional Prox: Decoupling Importance Estimation from Optimization for Continual Learning in Spiking Neural Networks▼1361.33
[PDF]Invariant Structural Distillation via Graph Condensation for History-Aware Graph Continual Learning▲9.2k2.67
[PDF]GLED-Net: A Global-Local Evidence Decomposition Network for Multimodal Fake News Detection▼1361.33
[PDF]When the Label Space Shrinks: Task-Adaptive Depth Compression via Recomputed Gradient-Residual Sensitivity▼1361.33
[PDF]The Score Is Not the Model: Four Protocol Failure Modes in Open Graph Benchmark Reporting▼1.2k1.67
[PDF]Wider Groups, Fewer Weights: Efficient Pseudo-Orthogonal Equivariance via Geometric Algebras▼4.3k2.00
Withdrawn or desk rejected (326)
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Never Stop Rewiring: Safe Continual Reinforcement Learning on Non-Resetting GraphsWithdrawn1.33