5 threads for a beginner in Web3, Crypto, NFTs 🚀

+ a BONUS at the end! 😍

1. Why Web3 matters by @cdixon

https://t.co/2UoyYvqhN8
2. WTF is Web 3 by @hey_bernie

https://t.co/jJsHXiP767
3. What is NFT in simple terms by @digitalpratik

https://t.co/Z7AeOyZtSr
4. Demystifying NFTs by @naval
https://t.co/Ue79ZWs2GT
5. What is wallet in NFT or Crypto or Web3 or DeFi world? by @digitalpratik

https://t.co/7yOJt1wU7T
BONUS: Educational Hub by @worldofwomennft

A place to know what are nfts, gas, eth, weth to buying nfts and avoiding scams!

https://t.co/30CjojeY5y

More from All

ChatGPT is a phenomenal AI Tool.

But don't limit yourself to just ChatGPT.

Here're 8 AI-powered tools you should try in 2023:

1. KaiberAI

@KaiberAI helps you generate beautiful videos in minutes.

Transform your ideas into the visual stories of your dreams with this Amazing Tool.

New features:
1. Upload your custom music
2. Prompt Templates
3. Camera Movements:

Check here

https://t.co/ivnDRf628L


2. @tldview TLDV

Best ChatGPT Alternative for meetings.

Make your meetings 10X more productive with this amazing tool.

Try it now:

https://t.co/vOy3sS4QfJ


3. ComposeAI

Use ComposeAI for generating any text using AI.

It’s will help you write better content in seconds.

Try it here:

https://t.co/ksj5aop5ZI


4. Browser AI

Use this AI tool to extract and monitor data from any website.

Train a robot in 2 minutes to do your work.

No coding required.

https://t.co/nNiawtUMyO
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