Related papers: Convergence Dynamics and Stabilization Strategies …

Recently, human motion analysis has experienced great improvement due to inspiring generative models such as the denoising diffusion model and large language model. While the existing approaches mainly focus on generating motions with…

Generating image variations, where a model produces variations of an input image while preserving the semantic context has gained increasing attention. Current image variation techniques involve adapting a text-to-image model to reconstruct…

Understanding convergent learning -- the degree to which independently trained neural systems -- whether multiple artificial networks or brains and models -- arrive at similar internal representations -- is crucial for both neuroscience and…

Deep learning systems achieve remarkable empirical performance, yet the stability of the training process itself remains poorly understood. Training unfolds as a high-dimensional dynamical system in which small perturbations to…

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterising the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first…

Learning predictive models for unlabeled spatiotemporal data is challenging in part because visual dynamics can be highly entangled in real scenes, making existing approaches prone to overfit partial modes of physical processes while…

Within the scaling laws paradigm, which underpins the training of large neural networks like ChatGPT and Llama, we consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon, a…

Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis. However, many existing systems rely on explicit modality switching,…

One potential disadvantage of social tagging systems is that due to the lack of a centralized vocabulary, a crowd of users may never manage to reach a consensus on the description of resources (e.g., books, users or songs) on the Web. Yet,…

Recursive prompting with large language models enables scalable synthetic dataset generation but introduces the risk of bias amplification. We investigate gender bias dynamics across three generations of recursive text generation using…

We provide an overview of the diffusion model as a method to generate new samples. Generative models have been recently adopted for tasks such as art generation (Stable Diffusion, Dall-E) and text generation (ChatGPT). Diffusion models in…

Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are…

Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions and/or relying on contextual cues and common-sense…

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the…

In the context of generative models, text-to-image generation achieved impressive results in recent years. Models using different approaches were proposed and trained in huge datasets of pairs of texts and images. However, some methods rely…

Diffusion models accomplish remarkable success in data generation tasks across various domains. However, the iterative sampling process is computationally expensive. Consistency models are proposed to learn consistency functions to map from…

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…

Text-to-image models are increasingly popular and impactful, yet concerns regarding their safety and fairness remain. This study investigates the ability of ten popular Stable Diffusion models to generate harmful images, including NSFW,…

Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in the training dataset, we often are more concerned with other…