AI ethics evidence index Search
Source-linked daily record
Evidence record 6581 · automatically gathered

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generativ

Record details

Published: 30 March 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

Aligning Recommendations with User Popularity Preferences

arXiv · 1 April 2026

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

SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment

arXiv · 26 March 2026

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

The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation

arXiv · 25 March 2026

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

Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation

arXiv · 25 March 2026

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

BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents

arXiv · 25 March 2026

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

Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation

arXiv · 5 April 2026

How to cite this record

ethics.ai (30 March 2026), “On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers,” evidence record 6581, https://ethics.ai/record/6581 (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.