Conditional Flow Matching for ML-Based Inverse Design Problems
cs.LG
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/huggingface/diffusers
Terminology
Sources
- EngiBench: A Framework for Data-Driven Engineering Design Research
- Flow Matching for Generative Modeling
- Conditional Generative Adversarial Nets
- Generative Adversarial Networks
- Denoising Diffusion Probabilistic Models
- Building Normalizing Flows with Stochastic Interpolants
- Improving and generalizing flow-based generative models with minibatch optimal transport
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Generative Design of Ship Propellers using Conditional Flow Matching
- Trajectory-Aware Flow Matching for Topology Optimisation
- On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow Matching
- How well do generative models solve inverse problems? A benchmark study
- Generative Inverse Design with Abstention via Diagonal Flow Matching
- Decoupled Weight Decay Regularization
- Adam: A Method for Stochastic Optimization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks