One of the most important areas of NLP is information extraction (IE), which takes unstructured text and turns it into structured knowledge. Many subsequent activities rely on IE as a prerequisite, including building knowledge graphs, knowledge reasoning, and...

In recent years, there has been remarkable progress in speech generation, achieving one-shot generation capability virtually indistinguishable from real human voice. The demand for lifelike speech synthesis is crucial for widespread adoption in modern AI applications,...

The constant visibility of hands in our daily activities makes them crucial for a sense of self-embodiment. The problem is the need for a digital hand model that is photorealistic, personalized, and relightable. Photorealism ensures a realistic visual representation,...

In artificial intelligence (AI), developers often face the challenge of efficiently working with many models. The struggle lies in managing different API signatures, preventing bottlenecks, and ensuring resilience in the face of errors. This complexity hinders the...

In audio processing, speaker diarization is a critical yet challenging task. This technique, pivotal in discerning individual voices in multi-speaker environments, holds immense value across various applications. From enhancing the clarity of conference calls to...

Integrating two-dimensional (2D) and three-dimensional (3D) data is a significant challenge. Models tailored for 2D images, such as those based on convolutional neural networks, need to be revised for interpreting complex 3D environments. Models designed for 3D...