embeddings
Embeddings are low-dimensional vector representations of data that capture semantic meaning and relationships between individual data points. In AI, embeddings are often used for tasks such as natural language processing and image recognition to facilitate efficient computation and improve neural network performance.
- A CLT for Polynomial GNNs on Community-Based Graphs
- Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
- Generalizing while preserving monotonicity in comparison-based preference learning models
- Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
- OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
- Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization
- Scaling Image Geo-Localization to Continent Level
- Soft Task-Aware Routing of Experts for Equivariant Representation Learning
- THUNDER: Tile-level Histopathology image UNDERstanding benchmark
- The Complexity of Finding Local Optima in Contrastive Learning
- UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification
- Unveiling Transformer Perception by Exploring Input Manifolds
- When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product
- ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data