Elastic Representations via Hyperbolic Geometry
cs.LG, cs.CV
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/arjunrkaushik/herl
Terminology
Sources
- Reducing Transformer Depth on Demand with Structured Dropout
- Matryoshka Diffusion Models
- DynaBERT: Dynamic BERT with Adaptive Width and Depth
- Matryoshka Query Transformer for Large Vision-Language Models
- Billion-scale similarity search with GPUs
- Hyperbolic Image Embeddings
- Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- Gecko: Versatile Text Embeddings Distilled from Large Language Models
- The Numerical Stability of Hyperbolic Representation Learning
- Poincar'e Embeddings for Learning Hierarchical Representations
- Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
- Nomic Embed: Training a Reproducible Long Context Text Embedder
- Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
- Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions
- Arctic-Embed 2.0: Multilingual Retrieval Without Compromise
- Hyperbolic Contrastive Learning
- SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
- Jasper and Stella: distillation of SOTA embedding models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis