Recent breakthroughs in deep learning have revolutionized protein sequence and structure
prediction. These advancements are built on decades of protein design efforts, and are …

Discrete diffusion models have emerged as powerful tools for high-quality data generation.
Despite their success in discrete spaces, such as text generation tasks, the acceleration of …

Non-autoregressive neural machine translation (NAT) models are proposed to accelerate
the inference process while maintaining relatively high performance. However, existing NAT …

In the era of information explosion, recommender systems are crucial for mitigating user
information overload by filtering out irrelevant information and suggesting preferred items or …

With the development of artificial intelligence, people are no longer satisfied with merely
classifying data 27 and have begun to explore how to generate new data. Currently, the …