10 threads that will teach you more about business than any MBA:

How to start a company (by @theryanking]

https://t.co/BpNzqANnX6
@theryanking Understand the financial performance of any business (by @AliTheCFO)

https://t.co/Zhf8DJd1lZ
@theryanking @AliTheCFO How to generate business ideas (by @SahilBloom)

https://t.co/vtkm4j3x87
@theryanking @AliTheCFO @SahilBloom Startup principles to scale your company (by @bbourque)

https://t.co/cqINEMzyIk
@theryanking @AliTheCFO @SahilBloom @bbourque A masterclass on writing (by @dickiebush)

https://t.co/en3eCAtEX0
@theryanking @AliTheCFO @SahilBloom @bbourque @dickiebush Business frameworks (by @david_perell)

https://t.co/LqNpopfv3S
@theryanking @AliTheCFO @SahilBloom @bbourque @dickiebush @david_perell Valuable lessons from Elon Musk (by @GrowthMaster_)

https://t.co/NHZmbfmPNr
@theryanking @AliTheCFO @SahilBloom @bbourque @dickiebush @david_perell Build a 7-figure business with free traffic (by @wizofecom)

https://t.co/fiCSkfpq9x
@theryanking @AliTheCFO @SahilBloom @bbourque @dickiebush @david_perell @wizofecom Habits to look for in hiring high performing employees (by @gregisenberg)

https://t.co/rCHsZJdqYw
@theryanking @AliTheCFO @SahilBloom @bbourque @dickiebush @david_perell @wizofecom @gregisenberg How to not f*ck up relationships (by [@ShaanVP)

https://t.co/ELlsVo5OpP
@theryanking @AliTheCFO @SahilBloom @bbourque @dickiebush @david_perell @wizofecom @gregisenberg @ShaanVP Thank you for reading!

If you enjoyed this thread:

1. Follow me @GrowthMaster_ to learn about business, marketing, and audience building.
2. RT the first tweet to share this thread with your audience.

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