Trang Vu

Anh Bui, Trang Vu, Long Vuong et al.

Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models by selectively unlearning undesirable concepts. The common principle of previous works to remove a specific concept is to map it to a fixed generic concept, such as a neutral concept or just an empty text prompt. In this paper, we demonstrate that this fixed-target strategy is suboptimal, as it fails to account for the impact of erasing one concept on the others. To address this limitation, we model the concept space as a graph and empirically analyze the effects of erasing one concept on the remaining concepts. Our analysis uncovers intriguing geometric properties of the concept space, where the influence of erasing a concept is confined to a local region. Building on this insight, we propose the Adaptive Guided Erasure (AGE) method, which \emph{dynamically} selects optimal target concepts tailored to each undesirable concept, minimizing unintended side effects. Experimental results show that AGE significantly outperforms state-of-the-art erasure methods on preserving unrelated concepts while maintaining effective erasure performance. Our code is published at {https://github.com/tuananhbui89/Adaptive-Guided-Erasure}.

Anh Bui, Trang Vu, Trung Le et al.

In this paper, we investigate the semantic collapsing problem in generative personalization, an under-explored topic where the learned visual concept ($V$) gradually shifts from its original textual meaning and comes to dominate other concepts in multi-concept input prompts. This issue not only reduces the semantic richness of complex input prompts like "a photo of $V$ wearing glasses and playing guitar" into simpler, less contextually rich forms such as "a photo of $V$" but also leads to simplified output images that fail to capture the intended concept. We identify the root cause as unconstrained optimisation, which allows the learned embedding $V$ to drift arbitrarily in the embedding space, both in direction and magnitude. To address this, we propose a simple yet effective training-free method that adjusts the magnitude and direction of pre-trained embedding at inference time, effectively mitigating the semantic collapsing problem. Our method is broadly applicable across different personalization methods and demonstrates significant improvements in text-image alignment in diverse use cases. Our code is anonymously published at https://github.com/tuananhbui89/Embedding-Adjustment

Manh Luong, Tamas Abraham, Junae Kim et al.

Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text. We introduce MCBench, a benchmark with 1196 scenarios spanning four safety categories that require integrating multiple modalities for accurate safety assessment. Each unsafe scenario is paired with a minimally different safe counterpart to assess model sensitivity. Our evaluations of state-of-the-art models reveal significant challenges. Omni LLMs struggle with subtle or non-physical risks but perform better when salient visual or acoustic cues are present. Analysis of reasoning traces shows that, although models can extract modality-specific information, they often fail to integrate these cues effectively for safety judgments. Our findings reveal that current Omni LLMs lack robust cross-modal reasoning in safety-critical settings, underscoring the need for improved architectures and training strategies for multimodal safety.