The role of injected noise in diffusion model generalization
cs.LG, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser
- The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning
- A Random Matrix Theory Perspective on the Consistency of Diffusion Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- 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