Related papers: Latent Guard: a Safety Framework for Text-to-image…
Text-to-image (T2I) diffusion models are popular for introducing image manipulation methods, such as editing, image fusion, inpainting, etc. At the same time, image-to-video (I2V) and text-to-video (T2V) models are also built on top of T2I…
The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data owners. Existing countermeasures, such…
In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit hallucination, generating descriptive content that deviates…
The rapid development of generative artificial intelligence has made text to video models essential for building future multimodal world simulators. However, these models remain vulnerable to jailbreak attacks, where specially crafted…
Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…
Text-to-image models can generate harmful images when presented with unsafe prompts, posing significant safety and societal risks. Alignment methods aim to modify these models to ensure they generate only non-harmful images, even when…
Recent text-to-image generation models have demonstrated impressive capability of generating text-aligned images with high fidelity. However, generating images of novel concept provided by the user input image is still a challenging task.…
One challenge in text-to-image (T2I) generation is the inadvertent reflection of culture gaps present in the training data, which signifies the disparity in generated image quality when the cultural elements of the input text are rarely…
Translating information between text and image is a fundamental problem in artificial intelligence that connects natural language processing and computer vision. In the past few years, performance in image caption generation has seen…
Text-to-image (T2I) generation has seen significant growth over the past few years. Despite this, there has been little work on generating diagrams with T2I models. A diagram is a symbolic/schematic representation that explains information…
A good Text-to-Image model should not only generate high quality images, but also ensure the consistency between the text and the generated image. Previous models failed to simultaneously fix both sides well. This paper proposes a Gradual…
Text-to-video (T2V) generative models have rapidly advanced and found widespread applications across fields like entertainment, education, and marketing. However, the adversarial vulnerabilities of these models remain rarely explored. We…
Recent spatial control methods for text-to-image (T2I) diffusion models have shown compelling results. However, these methods still fail to precisely follow the control conditions and generate the corresponding images, especially when…
Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereotypes). Existing debiasing methods, often designed for…
As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informative responses while avoiding the disclosure of harmful or…
How humans can effectively and efficiently acquire images has always been a perennial question. A classic solution is text-to-image retrieval from an existing database; however, the limited database typically lacks creativity. By contrast,…
Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…
Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended…
Warning: this paper contains content that may be inappropriate or offensive. As generative models become available for public use in various applications, testing and analyzing vulnerabilities of these models has become a priority. In this…
In recent years, text-to-image (T2I) diffusion models have gained significant attention for their ability to generate high quality images reflecting text prompts. However, their growing popularity has also led to the emergence of backdoor…