arXiv:2607. 03397v1 Announce Type: new Abstract: Text-to-Image diffusion models often propagate harmful bias inherited from the training data.
arXiv:2606. 09653v1 Announce Type: new Abstract: Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions.
arXiv:2603. 26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected.
arXiv:2607. 00402v1 Announce Type: cross Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts.
arXiv:2607. 06432v1 Announce Type: cross Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training.
arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas th...
arXiv:2607. 08337v1 Announce Type: new Abstract: Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models.
Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models. Current diffusion unlearning techniques determine the model update direction by either using alternatives of the target concept as an anchor or using empty prompts.
arXiv:2503. 07265v4 Announce Type: replace-cross Abstract: Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content.
arXiv:2606. 15819v1 Announce Type: cross Abstract: The rapid progress of visual autoregressive (VAR) models has unlocked a transformative frontier for high-fidelity text-to-image synthesis, while heightening concerns over the safety alignment of generated content.
arXiv:2511.22245v2 Announce Type: replace Abstract: Personalizing text-to-image diffusion models extends pretrained models to represent novel user-specific concepts from only a few reference images....
arXiv:2606. 10892v1 Announce Type: cross Abstract: To showcase products, merchants often incur substantial costs creating high-quality display images.
The paper introduces Mapping the Concept Landscape (MCL), a framework that replaces high‑dimensional feature embeddings with explicit sample‑level graphs of entities, events, and attributes for image‑caption pairs. By aggregating these graphs into a dataset‑level graph, MCL captures the global distribution of semantic concepts and identifies rare concepts. A greedy algorithm then selects samples to maximize coverage of under‑represented concepts, achieving better pruning efficiency and providing a transparent audit trail.