Gradient-Free Noise Optimization for Reward Alignment in Generative Models
Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to deterministic generators. A natural alternative is noise-space optimization, but existing approaches require backpropagation through the generator and reward pipeline, limiting applicability to differentiable settings. To address this, here we present ZeNO (Zeroth-order Noise Optimization), a gradient-free framework that formulates noise optimization as a
Record details
Published: 12 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment
arXiv · 12 May 2026
Rethinking external validation for the target population: Capturing patient-level similarity with a generative model
arXiv · 11 May 2026
Leveraging RAG for Training-Free Alignment of LLMs
arXiv · 11 May 2026
Interpretability Can Be Actionable
arXiv · 11 May 2026
Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
arXiv · 12 May 2026
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
arXiv · 11 May 2026
How to cite this record
ethics.ai (12 May 2026), “Gradient-Free Noise Optimization for Reward Alignment in Generative Models,” evidence record 4522, https://ethics.ai/record/4522 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.