SPC x Manifold: Omnimodal Action Models for Physical and Digital Agents

Moving from generation to reliable action has been a key capability researchers and AI practitioners have been pursuing over the past several years, and is a necessary component to realize digital agents.

​South Park Commons members & Manifold Researchers will overview some of the recent work in Vision, Language, Action models, give a sneak peak of new Omnimodal action models we are building, the dataset/benchmark we are using to train and test them, and an idea of how these models can be used to realize the promise of agents that can autonomously use software.

​Presenters: Harsh Sikka, Pranav Guruprasad

​About South Park Commons (SPC)

​​​​SPC is a technical community and venture fund dedicated to helping founders, researchers, and technologists figure out what to work on next—what we call the -1 to 0 stage of your career. We believe this is best accomplished in the most talent-dense community possible.

​​​​If you are exploring what's next, we encourage you to apply for SPC membership.