What is multimodality? A deep dive on multimodality in Gemma 3

5 955
8.6
Следующее
Популярные
71 день – 18914:29
Enhancing Reliability (Part 2)
Опубликовано 18 сентября 2025, 4:00
Explore the power of Gemma 3 and its ability to understand and integrate information from multiple sources, like images, text, and short videos. Aishwarya, a Research Scientist on the Gemma team leading the multimodal efforts, shares how Gemma 3 delivers impressive performance across a range of tasks, from answering questions to generating descriptive outputs, making it a versatile tool for developers and researchers alike.

Chapters:
0:00 - Introduction
0:00 - What is multimodality?
0:00 - What can Gemma 3 do?
0:00 - Powerful vision encoder
0:00 - Combining multilingual and multimodal

Subscribe to Google for Developers → goo.gle/developers

Speaker: Aishwarya Kamath
Products Mentioned: Gemma, Gemma 3
Свежие видео
1 день – 1 018 4002:06
Lew meets @looirobot …
9 дней – 43 16032:51
The Best 14" Gaming Laptops Right Now
13 дней – 3 0930:37
AI Stakes in Healthcare
автотехномузыкадетское