Understanding and Learning Prediction Targets in Diffusion Models
cs.LG, cs.CV
Submitted: 2026-01-29
Updated: 2026-11-12
Terminology
Sources
- Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training
- PixelFlow: Pixel-Space Generative Models with Flow
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Training Agents Inside of Scalable World Models
- Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
- Scalable Adaptive Computation for Iterative Generation
- An analytic theory of creativity in convolutional diffusion models
- Adam: A Method for Stochastic Optimization
- Back to Basics: Let Denoising Generative Models Denoise
- Flow Matching for Generative Modeling
- Progressive Distillation for Fast Sampling of Diffusion Models
- Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
- Deep Information Propagation
- Score-Based Generative Modeling through Stochastic Differential Equations
- PixNerd: Pixel Neural Field Diffusion
- DDT: Decoupled Diffusion Transformer
- Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
- Diffusion Transformers with Representation Autoencoders
Related papers
- 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
- (Mis)generalization of Helpful-Only Fine-tuning
- Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine