NeurIPS 2025PastLarge language models
Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks
NEGEL 2025
- Submission deadline
- Sep 9, 2025, 12:00 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (25)
Fetched from OpenReview (v2) on 2026-06-10.
A geometric framework for momentum-based optimizers for low-rank training
Any-Subgroup Equivariant Networks via Symmetry Breaking
AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions
Attentive Multi-Channel Molecular Representation in Drug–Target Affinity Prediction
Biological Pathway Informed Models with Graph Attention Networks (GATs)
Boundary Guidance for Efficient 3D CT Vision–Language Reasoning
CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning
Contrastive MIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning
CoPE: Enhanced Transformer with Complex Positional Encoding
Differentiable Lifting for Topological Neural Networks
Extracting information from fine-tuned weights
Geometry-Aware Backdoor Attacks: Leveraging Curvature in Hyperbolic Embeddings
GLASS: A Differentiable Geometric Alignment Layer on Manifolds and Graphs via Learned Slices and Soft Optimal Transport
HypBench: Hyperbolic Benchmark for Graph Neural Network Performance
Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies
HyperHELM: Hyperbolic Hierarchy Encoding for mRNA Language Modeling
Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry
Memorization-Compression Cycles Improve Generalization
ONG: Orthogonal Natural Gradient Descent
Quantum-Inspired Complex Transformers: Resolving the Fundamental Algebraic Ambiguity for Enhanced Neural Representations
Riemannian Fuzzy K-Means on Product Manifolds
RL's Razor: Why On-Policy Reinforcement Learning Forgets Less
SphereEdit: Geometric Control for Composable Diffusion-Based Image Editing
Towards Intrinsic Topology Search: Differentiable Isomap Application
When Curvature Beats Dimension: Euclidean Limits and Hyperbolic Design Rules for Trees