Moderna CEO Stephane Bancel was previously CEO of bioMerieux in France from 07-10.

Alain Merieux, who owns bioMerieux, was instrumental in the creation of the Wuhan Institute of Virology P4 Lab.

The same people who helped create the virus, also helped to create the vaccines...

Moderna partnered with French Pasteur Institute in 2015 to develop mRNA vaccine technology.

Pasteur Institute partnered with the Wuhan P4 Laboratory in 2017 along with the Merieux Foundation to study emerging viruses...
https://t.co/yFsHwrNYaK
https://t.co/9M5lydBKhM
Nobel prize winning scientist Luc Montagnier asserts that Sars-Cov-2 is man-made and originated from the Wuhan Institute of Virology.

Montagnier did extensive work with the Pasteur Institute in France which was partnered with the Wuhan P4.
https://t.co/aPzJ2sSqFe
Merieux Foundation & the Chinese government have worked together since 1965, and partnered to study emerging pathogens in Africa in 2015.

Their research included "PATHOGENS CARRIED BY BATS" that provoke respiratory diseases.

🚨🚨🚨
https://t.co/gVwpT0ssqI

More from All

How can we use language supervision to learn better visual representations for robotics?

Introducing Voltron: Language-Driven Representation Learning for Robotics!

Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z

🧵👇(1 / 12)


Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.

Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)

The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (
https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).

The secret is *balance* (3/12)

Starting with a masked autoencoder over frames from these video clips, make a choice:

1) Condition on language and improve our ability to reconstruct the scene.

2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)

By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.

Why is the ability to shape this balance important? (5/12)

You May Also Like