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
796 results for “area:"learning on graphs and other geometries & topologies"” in ICLR 2027. 153 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reasoning or Retrieval? Diagnosing LLM Failures on Temporal Knowledge Graphs with Ground-Truth Evidence▼5.8k2.33
[PDF]When Is Reweighting Not Enough? A Hodge Certificate for Rewiring Noisy and Incomplete Graphs▼5.8k2.33
[PDF]Universal Diffeomorphic Representation Learning on SPD Manifolds via the Spline-Pullback Metric▼4.3k2.20
[PDF]GraphScale: Scaling Controlled Graph Generation through Hierarchical Constraint Composition▼1.2k1.67
[PDF]LeGramJEPA: Negative-Free Multimodal Graph Foundation Models in Latent Space with Volumetric Alignment and SIGReg▼1.2k1.67
[PDF]Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures▼1.2k1.67
[PDF]VisFlow: Interpretable Flow Matching for Visibility Reconstruction, Characterization, and Recognition▼5.8k2.33
[PDF]FlowGMAE: Physics-Constrained Virtual Sensing for Anomaly Detection Beyond Sensor Coverage▲5.4k3.00
[PDF]OWNERSHIP IS THE MISSING DECLARATION: DECIDING RELATIONAL TARGET LEAKAGE FROM THE SCHEMA▼4.3k2.00
[PDF]GraphSteer: Soft Edge Reweighting via Informative Leiden Subgraphs for Graph Out-of-Distribution Generalization▼1611.50
[PDF]What Do Hypergraph Benchmarks Measure? Feature Paths, Evaluation Protocols, and Modular Constraints▼1361.33
[PDF]What Soft Clustering Objectives Compute, When They Are Tight, and What Softness Buys: The Case of Soft Structural Entropy▼1361.33
[PDF]Wallpaper Net: A general Blueprint for Wallpaper-Group-Equivariant Graph Neural Networks▼1.2k3.00
[PDF]SURF: Expressive Structural Adaptation for Billion-Scale Link Prediction with Graph Foundation Models▲432.75
[PDF]Learning Higher-Order Interactions from Incomplete Spatiotemporal Data with Mixtures of Hypergraph Laplacians▲3.0k2.33
[PDF]Two Negatives Make a Positive: Dual Negative Learning for Continual Knowledge Graph Embedding▲3.0k2.33
[PDF]RhinoNet: Unsupervised learning for phenoscaping and generation of high dimensional point clouds▲3952.67
[PDF]Serialization Is Not Enough: From Presentation to Utilization in LLM-Based Graph Prediction▲3952.67
Withdrawn or desk rejected (153)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]From Euclidean to Riemannian: Boundary-Aware Geodesic Oversampling for Class-Imbalanced GraphsWithdrawn2.00
[PDF]Caustic Spectroscopy: Identifiability and Acquisition Limits of Topological Event TimingWithdrawn2.00
[PDF]Graphs are Evidence, Not CircuitsDesk rejected