Cross-Time Directional Selection in Diffusion Sampling
cs.LG
Submitted: 2026-10-04
Updated: 2026-10-04
Sources
- A Quantitative Approximation Framework for Flow Distillation in Diffusion Models
- The Geometry of Phase Transitions in Generative Dynamics via Projection Caustics
- Your diffusion model secretly knows the dimension of the data manifold
- Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion
- Spatial Transport of Integration Error in Generative ODEs
- Scalable Diffusion Models with Transformers
- Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
- Denoising Diffusion Implicit Models
- DINOv2: Learning Robust Visual Features without Supervision
- Deep Residual Learning for Image Recognition
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