AI ethics evidence index Search
Source-linked daily record
Evidence record 4023 · automatically gathered

Stitched Value Model for Diffusion Alignment

For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challenging because the reward is defined for clean output images, but the alignment procedure requires value function estimates at noisy intermediate latents. Existing methods resort to Tweedie-style or Monte Carlo approximations, trading off estimator bias against computational cost: Tweedie estimates are efficient but bias

Record details

Published: 19 May 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

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.

Shared topic: Bias & fairness · Shared topic: Safety & alignment

LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition

arXiv · 19 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Graph Alignment Topology as an Inductive Bias for Grounding Detection

arXiv · 21 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Representation Alignment Rests on Linear Structure

arXiv · 22 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment

arXiv · 22 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot

arXiv · 22 May 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation

arXiv · 24 May 2026

How to cite this record

ethics.ai (19 May 2026), “Stitched Value Model for Diffusion Alignment,” evidence record 4023, https://ethics.ai/record/4023 (originally published by arXiv).

JSON

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.