Lucas Beyer
2nd September, 2024, 1:00pm - 2:00 PM (GST)
| Title: | Vision in the age of LLMs |
| Affiliation: | Google DeepMind (formerly Brain) Zürich |
| Abstract: | I will discuss how vision has changed with the integration of language and the appearance of LLMs, with focus on the recent works of our group. Specifically, I will spend a bit of time on SigLIP, and on the PaLI line of work. Depending on time, I might also cover UViM and RL-tuning for vision, as well as fairness and cultural diversity in VLMs (our recent "No Filter" paper) |
| Bio: | Lucas grew up in Belgium wanting to make video games and their AI. He went on to study mechanical engineering at RWTH Aachen in Germany, then did a PhD in robotic perception and computer vision there too. Now, he is a staff research scientist at Google DeepMind (formerly Brain) in Zürich, leading multimodal vision-language research. |