There are more than 3,000 TED Talks.

Here are 10 TED Talks that will change the way you think forever:

1. Do schools kill creativity?

https://t.co/xlNTAUvVNq
2. How to make stress your friend

https://t.co/Weg5n1Mf9d
3. How to know your life purpose in 5 minutes

https://t.co/25ospTdSRX
4. The puzzle of motivation

https://t.co/TNoXkC097b
5. The power of introverts

https://t.co/PA6DoUgRSk
6. How great leaders inspire action

https://t.co/Y0yGukgeOG
7. What makes a good life? Lessons from the longest study on happiness

https://t.co/q2c6zq7Cm8
8. How to gain control of your free time

https://t.co/VkHeURoORF
9. 10 ways to have a better conversation

https://t.co/KyEvXBTEdX
10. The surprising habits of original thinkers

https://t.co/KINyLVYsG6
Are you feeling stuck and need some extra push to reach your goals?

"Murder Misery-30 Day Program" will help you to:

- Controll your beliefs
- Change your habits
- Reach your goals

Get your copy here: 👇 https://t.co/czh1Oyzmeh
If you enjoyed this thread please:

- like and rt the first tweet
- follow me @MentalUnleash

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