Microsoft

VALL-E Family

VALL-E 2 is the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time. Building upon the ...

Word and PowerPoint get automatic, on-device Alt Text on Copilot+ PCs

Microsoft has unveiled a new feature for Copilot+ PCs that utilizes on-device NPUs to automatically generate rich, ...
IEEE

Automated Commit Message Generation With Large Language Models: An Empirical Study and Beyond

Abstract: Commit Message Generation (CMG) approaches aim to automatically generate commit messages based on given code diffs, which facilitate collaboration among developers and play a critical role ...
The Debrief

“Turn Ideas into Physical Objects”: If You Describe an Object, This AI-Driven Robot Can Build It

MIT and Google DeepMind researchers have created an AI-driven robot that can turn ideas into physical objects with only ...
IEEE

Homogeneous and Heterogeneous Feature Learning Based on Large Models for Unsupervised Text-to-Image Person Re-Identification

Abstract: Text-to-image person re-identification (TIReID) aims to identify and retrieve target pedestrians according to given textual queries. Driven by enormous annotated data, existing supervised ...

The Race to Build the World’s Best Friend

Instead ChatGPT has become perhaps the most successful consumer product in history. In just over three years it has ...