EGLOCE erases target concepts in diffusion models at inference time by optimizing latents with dual energy guidance that repels unwanted concepts while retaining prompt alignment.
Forget-me-not: Learning to for- get in text-to-image diffusion models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4verdicts
UNVERDICTED 4representative citing papers
Unlearning methods that strongly erase concepts from text-to-image diffusion models consistently degrade performance on attribute binding, spatial reasoning, and counting tasks.
TokenTrace watermarks diffusion generations by jointly perturbing prompt embeddings and latent noise, enabling query-driven recovery of multiple independent concepts from one image.
Diffusion models show distinct patterns of recognizing versus replicating culturally iconic references, with recognition linked to data frequency, textual uniqueness, popularity, and creation date rather than simple copying.
citing papers explorer
-
EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure
EGLOCE erases target concepts in diffusion models at inference time by optimizing latents with dual energy guidance that repels unwanted concepts while retaining prompt alignment.
-
Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
Unlearning methods that strongly erase concepts from text-to-image diffusion models consistently degrade performance on attribute binding, spatial reasoning, and counting tasks.
-
TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery
TokenTrace watermarks diffusion generations by jointly perturbing prompt embeddings and latent noise, enabling query-driven recovery of multiple independent concepts from one image.
-
The Persistence of Cultural Memory: Investigating Multimodal Iconicity in Diffusion Models
Diffusion models show distinct patterns of recognizing versus replicating culturally iconic references, with recognition linked to data frequency, textual uniqueness, popularity, and creation date rather than simple copying.