Global Transport Couplings for Classifier-Free Guided Flows
cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- The Coupling Within: Flow Matching via Distilled Normalizing Flows
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Expected Batch Optimal Transport Plans and Consequences for Flow Matching
- Weighted Conditional Flow Matching
- CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
- Minibatch optimal transport distances; analysis and applications
- Classifier-Free Diffusion Guidance
- Scalable Adaptive Computation for Iterative Generation
- Optimal Transport Flow Matching by Design
- Non-Denoising Forward-Time Diffusions
- Movie Gen: A Cast of Media Foundation Models
- StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
- Parallel Decoding Distillation for Fast Image and Video Generation
- Measure-to-measure Regression with Transformers
- Analysis of Classifier-Free Guidance Weight Schedulers
- Guided Flows for Generative Modeling and Decision Making
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