FlowGuard detects unsafe content during diffusion image generation via linear latent decoding and curriculum learning, outperforming prior methods by over 30% F1 while reducing GPU memory by 97% and projection time to 0.2 seconds.
arXiv preprint arXiv:2303.07345 , year=
5 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
5
Pith papers citing it
2
external citations · external index
representative citing papers
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
DragNUWA integrates text, image, and trajectory controls into a diffusion video model using a Trajectory Sampler, Multiscale Fusion, and Adaptive Training to enable fine-grained open-domain video generation.
citing papers explorer
-
FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
FlowGuard detects unsafe content during diffusion image generation via linear latent decoding and curriculum learning, outperforming prior methods by over 30% F1 while reducing GPU memory by 97% and projection time to 0.2 seconds.
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
-
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
-
DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
DragNUWA integrates text, image, and trajectory controls into a diffusion video model using a Trajectory Sampler, Multiscale Fusion, and Adaptive Training to enable fine-grained open-domain video generation.