Yangyang Shi

This article discusses the developments in optical character recognition for natural scenes.

2025-10-04T08:49:42+00:00 ― 8 min read

A new approach enhances audio generation by aligning audio with text descriptions.

2025-09-11T07:13:25+00:00 ― 5 min read

Essential rules for submitting papers to NeurIPS 2024.

2025-07-21T22:01:00+00:00 ― 4 min read

A method for training language models using focused data selection techniques.

2025-06-07T05:09:36+00:00 ― 6 min read

Keeping AI conversations safe on the go with Llama Guard.

2025-05-20T23:31:39+00:00 ― 6 min read

SyncFlow merges audio and video generation for seamless content creation.

2025-04-05T10:21:54+00:00 ― 4 min read

MASV model enhances voice verification, ensuring security and efficiency.

2025-02-27T10:03:54+00:00 ― 5 min read