Multimodal datasets are a critical component in recent breakthroughs such as CLIP, Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the machine...
Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of training on large amounts of noisy image-text data, without relying on expensive accurate labels used in standard vision unimodal supervised learning. The resulting models showed...
Over-squashing and over-smoothing are two critical issues, that limit the capabilities of graph neural networks (GNNs). While over-smoothing eliminates the differences between nodes making them indistinguishable, over-squashing refers to the inability of GNNs to...
Our study reveals new theoretical insights into over-smoothing and feature over-correlation in deep graph neural networks. We show the prevalence of invariant subspaces, demonstrating a fixed relative behavior that is unaffected by feature transformations. Our work...
We propose Social Diffusion, a novel method for shortterm and long-term forecasting of the motion of multiple persons as well as their social interactions. Jointly forecasting motions for multiple persons involved in social activities is inherently a challenging...
In this paper, we present an inverse rendering method for the simple reconstruction of shape and appearance of real-world objects from only roughly calibrated RGB images captured under collocated point light illumination. To this end, we gradually reconstruct the...
