conftrace_

safety guidance

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

diffusion model (2) text-to-image generation (2) adaptive safety direction (1) category-aligned steering (1) harmful conflicts (1) token optimization (1) safe generation (1) harmful content detection (1) generative model (1) content moderation (1)

Papers

When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance CVPR 2026 Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization CVPR 2025