Multimodal Weekly 28: Rethinking Diffusion Models Training and Evaluating Multimodal Retrieval Systems
In the 28th session of Multimodal Weekly, we will dive into the latest research in multimodal generation and multimodal retrieval.
✅ Jeremy Kim and William Go, ML Research Scientists at Twelve Labs, will give a presentation on rethinking diffusion models training as multi-task learning.
✅ Jheng-Hong Yang, Ph.D. Student at the University of Waterloo, will give a presentation on assessing the frontier of multimodal search in multi(wiki)media wilds.
Check out these papers:
Join the Multimodal Minds community and sign up below to receive an invite to the Zoom webinar link!
Multimodal Weekly is organized by Twelve Labs, a startup building multimodal foundation models for video understanding. Learn more about Twelve Labs here: https://twelvelabs.io/