arXiv AI
Jul 28
LU-500: A Logo Benchmark for Concept Unlearning
arXiv:2607. 24101v1 Announce Type: cross Abstract: Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models.
LU-500: A Logo Benchmark for Concept Unlearning
Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations, however, mostly study targets that dominate the whole image, such as styles, broad object categories, or portrait-like identities, leaving company logos comparatively underexamined.
Related stories
arXiv Machine Learning
Jul 28
To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion
arXiv:2607. 23492v1 Announce Type: cross Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while preserving model utility on benign concepts.
arXiv AI
Jul 15
Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models
arXiv:2509. 22415v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect.
Hugging Face Trending Papers
Jul 6
Erasing Without Collateral Damage: Precise Concept Removal in Diffusion Models
Training-free concept erasure is an attractive mechanism for controlling text-to-image diffusion models, but precise erasure often comes at the cost of damaging semantically related non-target concepts. Existing value-space methods remove the component of each cross-attention value along the target concept direction, implicitly treating target identity and shared visual structure as the same signal.
Hugging Face Trending Papers
Jul 7
AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models
Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.
arXiv AI
Jul 8
TILDE: TILt-based Distributional Erasure for Concept Unlearning
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 AI
Jul 29
AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models
arXiv:2602. 09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs).
Hugging Face Trending Papers
Aug 4
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora. Removing such knowledge is essential for building trustworthy AI systems.
arXiv AI
Aug 12
Token-Based Detection of Spurious Correlations in Vision Transformers
arXiv:2509. 04009v2 Announce Type: replace-cross Abstract: Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, potentially leading to correct predictions based on incorrect or unintended but statistically relevant signals.
arXiv AI
Jul 22
Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models
arXiv:2607. 18695v1 Announce Type: cross Abstract: A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors.
arXiv AI
Aug 5
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
arXiv:2608. 03791v1 Announce Type: new Abstract: Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora.
Hugging Face Trending Papers
Jul 9
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
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.