Department of Computer Science - University of Texas at Austin

Adaptive Anatomy: 3D Models That Fit Every Form

Researchers at The University of Texas at Austin recently received support from the National Science Foundation (NSF) to ...
The Christian Science Monitor

Most schools are wary of AI. This one is embracing it.

Teachers are grappling with how to incorporate artificial intelligence into education. A handful of schools are structuring ...
Booth School of Business

Why AI Models Work When Theory Suggests They Shouldn’t

In recent years, something unexpected has been happening in artificial intelligence. Modern AI appears to be breaking a rule that statisticians have preached for nearly a century: Keep models in a ...
IEEE

Visual Class Incremental Learning With Textual Priors Guidance Based on an Adapted Vision-Language Model

Abstract: An ideal artificial intelligence (AI) system should have the capability to continually learn like humans. However, when learning new knowledge, AI systems often suffer from catastrophic ...
IEEE

Adapt and Feature Translation for Class-Incremental Learning with Pre-Trained Models

Abstract: Class-incremental learning (CIL) aims to enable a learning system to continuously learn new information. Although pre-trained models (PTMs) exhibit strong performance in CIL, the lack of ...