Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
Modality translation is inherently under-constrained, as multiple cross-modal mappings may yield the same marginals. Recent work has shown that diffusion bridges are effective for this task. However, most existing approaches rely on fully paired datasets, thereby imposing a single data-driven constraint. We propose a diffusion-bridge framework that characterizes the space of admissible solutions and restricts it via alignment constraints, treating paired supervision as an optional heuristic rath
Record details
Published: 3 May 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · 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.
AI Alignment Amplifies the Role of Race, Gender, and Disability in Hiring Decisions
arXiv · 2 May 2026
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
arXiv · 4 May 2026
Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
arXiv · 2 May 2026
Brainrot: Deskilling and Addiction are Overlooked AI Risks
arXiv · 5 May 2026
Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment
arXiv · 1 May 2026
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
arXiv · 6 May 2026
How to cite this record
ethics.ai (3 May 2026), “Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges,” evidence record 5043, https://ethics.ai/record/5043 (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.