Join us to learn how the Text-Conditional Image Generation field has evolved in recent years.
Oleksandr Skurzhanskyi, Applied Research Scientist at Grammarly, will be leading a talk to review the current state of the Text-Conditional Image Generation field, available datasets, and automated metrics.
We’ll take a look at models starting from Generative Adversarial Networks to the recently released Imagen (from Google) and DALL·E 2 (from OpenAI). We’ll also discuss current progress and trends. No prior knowledge of text2image is required. Join us!
About the speaker:
Oleksandr Skurzhanskyi is an Applied Research Scientist at Grammarly, leading a project that has helped grow the capabilities of Grammarly’s writing assitance to go way beyond grammar. He has six years of experience in the machine learning field and is interested in such topics as self-supervised learning, non-autoregressive text generation, and multimodal learning.