Self-Supervised Learning of Universal Latent Spaces for Operator Learning
cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Project page: https://daedalus.ethz.ch
Terminology
Sources
- Spatial Functa: Scaling Functa to ImageNet Classification and Generation
- Scaling Laws for Neural Language Models
- Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science
- Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
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