Related papers: I Learn to Diffuse, or Data Alchemy 101: a Mnemoni…
Recent breakthroughs in generative AI have opened the door to new research perspectives in the domain of art and cultural heritage, where a large number of artifacts have been digitized. There is a need for innovation to ease the access and…
Open Science, Reproducible Research, Findable, Accessible, Interoperable and Reusable (FAIR) data principles are long term goals for scientific dissemination. However, the implementation of these principles calls for a reinspection of our…
Citations are the cornerstone of knowledge propagation and the primary means of assessing the quality of research, as well as directing investments in science. Science is increasingly becoming "data-intensive", where large volumes of data…
We present a framework for high-fidelity product image recontextualization using text-to-image diffusion models and a novel data augmentation pipeline. This pipeline leverages image-to-video diffusion, in/outpainting & negatives to create…
Diffusion models have achieved state-of-the-art performance in generating images, audio, and video, but their adaptation to text remains challenging due to its discrete nature. Prior approaches either apply Gaussian diffusion in continuous…
Interest in tracing the research interests of scientific researchers is rising, and particularly that of predicting a researcher's knowledge trajectories beyond their current foci into potential inter-/cross-/multi-disciplinary…
Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ…
Diffusion condensation is a dynamic process that yields a sequence of multiscale data representations that aim to encode meaningful abstractions. It has proven effective for manifold learning, denoising, clustering, and visualization of…
Diffusion models have shown remarkable abilities in generating realistic and high-quality images from text prompts. However, a trained model remains largely black-box; little do we know about the roles of its components in exhibiting a…
I think that the main reason why we do not understand the general principles of how knowledge works (and probably also the reason why we have not yet designed and built efficient machines capable of artificial intelligence), is not the…
Recent text-to-image diffusion models are able to learn and synthesize images containing novel, personalized concepts (e.g., their own pets or specific items) with just a few examples for training. This paper tackles two interconnected…
Calculus and geometry are ubiquitous in the theoretical modelling of scientific phenomena, but have historically been very challenging to apply directly to real data as statistics. Diffusion geometry is a new theory that reformulates…
In the era of intelligent computing, computational progress in text processing is an essential consideration. Many systems have been developed to process text over different languages. Though, there is considerable development, they still…
Knowledge is the most precious asset of humankind. People extract the experience from the data that provide for us the reality through the feelings. Generally speaking, it is possible to see the analogy of knowledge elaboration between…
The art of the scientific presentation -- much like the art of the perfect plot, the art of the compelling proposal, and the art of the killer job application -- is generally not something we're taught in school. Therefore, in classic…
We present a method for producing documentary-style content using real-time scientific visualization. We produce molecumentaries, i.e., molecular documentaries featuring structural models from molecular biology. We employ scalable methods…
Taking advantage of the many recent advances in deep learning, text-to-image generative models currently have the merit of attracting the general public attention. Two of these models, DALL-E 2 and Imagen, have demonstrated that highly…
Deep learning (DL) methods typically require large datasets to effectively learn data distributions. However, in the medical field, data is often limited in quantity, and acquiring labeled data can be costly. To mitigate this data scarcity,…
Research on Digital Humanities (DH) has been boosted due to the investment in technology for developing access and interaction tools for handling Humanities and Heritage data. The availability of these tools lowers the distance between DH…
We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modeling to handle inputs…