SinAE: A Single-Architecture Flow-Matching Autoencoder for Cross-Domain Atomic Systems
cs.LG
Submitted: 2026-07-14
Updated: 2026-11-08
Terminology
Sources
- Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generation
- FlowMM: Generating Materials with Riemannian Flow Matching
- Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materials
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- ProteinBench: A Holistic Evaluation of Protein Foundation Models
- Fast protein backbone generation with SE(3) flow matching
- UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials
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