Scientific discovery in the age of artificial intelligence

H Wang, T Fu, Y Du, W Gao, K Huang, Z Liu… - Nature, 2023‏ - nature.com
Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment
and accelerate research, hel** scientists to generate hypotheses, design experiments …

Diffusion models: A comprehensive survey of methods and applications

L Yang, Z Zhang, Y Song, S Hong, R Xu, Y Zhao… - ACM Computing …, 2023‏ - dl.acm.org
Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Identifying and mitigating vulnerabilities in llm-integrated applications

F Jiang - 2024‏ - search.proquest.com
Large language models (LLMs) are increasingly deployed as the backend for various
applications, including code completion tools and AI-powered search engines. Unlike …

Scaling rectified flow transformers for high-resolution image synthesis

P Esser, S Kulal, A Blattmann, R Entezari… - … on machine learning, 2024‏ - openreview.net
Diffusion models create data from noise by inverting the forward paths of data towards noise
and have emerged as a powerful generative modeling technique for high-dimensional …

Voicebox: Text-guided multilingual universal speech generation at scale

M Le, A Vyas, B Shi, B Karrer, L Sari… - Advances in neural …, 2023‏ - proceedings.neurips.cc
Large-scale generative models such as GPT and DALL-E have revolutionized the research
community. These models not only generate high fidelity outputs, but are also generalists …

Illuminating protein space with a programmable generative model

JB Ingraham, M Baranov, Z Costello, KW Barber… - Nature, 2023‏ - nature.com
Three billion years of evolution has produced a tremendous diversity of protein molecules,
but the full potential of proteins is likely to be much greater. Accessing this potential has …

Flow matching for generative modeling

Y Lipman, RTQ Chen, H Ben-Hamu, M Nickel… - arxiv preprint arxiv …, 2022‏ - arxiv.org
We introduce a new paradigm for generative modeling built on Continuous Normalizing
Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present …

Lion: Latent point diffusion models for 3d shape generation

A Vahdat, F Williams, Z Gojcic… - Advances in …, 2022‏ - proceedings.neurips.cc
Denoising diffusion models (DDMs) have shown promising results in 3D point cloud
synthesis. To advance 3D DDMs and make them useful for digital artists, we require (i) high …

Spatio-temporal graph neural networks for predictive learning in urban computing: A survey

G **, Y Liang, Y Fang, Z Shao, J Huang… - … on Knowledge and …, 2023‏ - ieeexplore.ieee.org
With recent advances in sensing technologies, a myriad of spatio-temporal data has been
generated and recorded in smart cities. Forecasting the evolution patterns of spatio-temporal …

A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection

M **, HY Koh, Q Wen, D Zambon… - … on Pattern Analysis …, 2024‏ - ieeexplore.ieee.org
Time series are the primary data type used to record dynamic system measurements and
generated in great volume by both physical sensors and online processes (virtual sensors) …