Learning Noise Optimization for Reward Alignment in Few-Step Generative Models
cs.LG, cs.AI, cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/christophschuhmann/improved-aesthetic-predictor
Terminology
Sources
- Mean Flows for One-step Generative Modeling
- Gradient-Free Noise Optimization for Reward Alignment in Generative Models
- PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models
- DINOv2: Learning Robust Visual Features without Supervision
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- Consistency Models
- Riemannian MeanFlow
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- Fast protein backbone generation with SE(3) flow matching
- SE(3) diffusion model with application to protein backbone generation
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