DRIFT: Disentangled Responsive-Invariant Flow Transport for Single-Cell Perturbation Prediction
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/MustaphaBounoua/drift
Sources
- Self-supervised learning of Split Invariant Equivariant representations
- Towards a Definition of Disentangled Representations
- What Makes a Representation Good for Single-Cell Perturbation Prediction?
- Flow Matching for Generative Modeling
- Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling
- Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
- Improving and generalizing flow-based generative models with minibatch optimal transport
- Predicting Cellular Responses with Variational Causal Inference and Refined Relational Information
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks