Sean KirmaniMember of Technical Staff · OpenAIResearcher↗
Researcher
OpenAIMember of Technical Staff
Xu introduced AttnGAN, a text-to-image system that focuses on the most relevant words while drawing different parts of a picture. This attention-based design helped models produce images with finer details that better matched complicated written descriptions.
OpenAI2019-presentWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Reported GPT-4's capabilities, limitations and safety evaluations as a text-and-image input model.
Whisper learns speech transcription and translation from large amounts of paired audio and text.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 7, 2026 · Checked for accuracy and new information.