Anthony Hu

Research at General Intuition @gen_intuition. I like building scalable world models from high-dimensional videos in order to train intelligent agents.

[Anthony Hu @hu_anth]

@hudsonyeoce thanks Hudson! seems like you've been through the tech report 👀

[Anthony Hu @hu_anth]

Presenting MIRA, a multiplayer world model you can experience live from your browser. Play a dream of Rocket League with your friends using your keyboard.

Try the live demo here: https://t.co/1AE6fVAowK

[Anthony Hu @hu_anth]

@yangcliu @gen_intuition medal data was only used to get the APM distribution of human gamers, to compare with the APM distribution of bots. we noticed they were very different, but regardless humans could play in the world model (trained from bots data only) just fine

[Vincent Micheli @micheli_vincent]

Proud to release MIRA, a multiplayer world model!

MIRA learns the dynamics of a 4 player game of Rocket League. It runs in real-time and you can interact with other humans or the policies simulated by the model.

World models have never been more fun to explore, give it a try!

[Anthony Hu @hu_anth]

(7/7) Technical report: https://t.co/BSsaxJgY7j
Blog: https://t.co/Sp7LmZruzP

[Anthony Hu @hu_anth]

(6/7) 💻 We're open sourcing the dataset and training+inference code. This research was developed by @GeneralIntuition and @Kyutai, in collaboration with Epic Games.

[General Intuition @gen_intuition]

Launching @kyutai_labs x @Gen_intuition - research collab at the frontier

World models and agents capable of spatiotemporal reasoning are the next frontier. As builders of this technology, we have a responsibility to educate.

This is impossible without both unique data and world-leading talent. Through our research collaboration, both labs will share data and talent seamlessly.

- The necessary data lives inside only a few companies, and isn’t available on the internet. @gen_intuition owns the largest, most diverse, ground truth action labelled dataset. @Kyutai_labs utilizes the data for open research, resuming their culture of publishing on the frontier

- Talent moves between the two labs, switching freely between open-ended research and application

Join us in NYC and Europe - open roles below

https://t.co/3dB89sWH17 & https://t.co/QQy13ioToh

[Anthony Hu @hu_anth]

https://t.co/l9uKeQl62x

[General Intuition @gen_intuition]

Introducing General Intuition and our $133.7M Seed from Khosla Ventures, General Catalyst, and Raine. We build foundation models and general agents for environments that require deep spatial and temporal reasoning.

[Anthony Hu @hu_anth]

I'm starting a new journey building general agents and world models for video games at General Intuition. The past 6 years at Wayve working on self-driving cars have been an absolute blast, where I've learned so much alongside wonderful colleagues.

[Anthony Hu @hu_anth]

It's a unique playground to build agents with a general intuition. Working with the @gen_intuition team has been so much fun so far, and I can't wait to explore what's ahead of us!

[Vincent Micheli @micheli_vincent]

We’re starting a company to build the next frontier of embodied intelligence - General Intuition

We believe the time has come to move from words to worlds, and we’re developing foundation models capable of acting in any environment. Starting with video games!

[Wayve @wayve_ai]

Introducing GAIA-2 🌎Generative world modeling just stepped up a gear.

GAIA-2 is the latest development of Wayve’s video-generative world model tailored for driving. GAIA-2 offers richer, more realistic, and highly controllable synthetic driving scenarios, accelerating Wayve’s path to safe driver assistance and automated driving at scale.

Learn more about GAIA-2 in our Blog: https://t.co/1Rfi5ppiZQ

#GAIA2 #GAIA #EmbodiedAI

[Wayve @wayve_ai]

It’s #GAIA1 world, we just drive in it.
Generate realistic driving videos using only prompts.
See how it works below 🧵

[Wayve @wayve_ai]

Wayve presents Model-based Imitation LEarning (MILE): a method to jointly learn a world model and a driving policy from an offline corpus of driving data. This model is another step in achieving a more generalisable driver - paper to appear at #NeurIPS2022 https://t.co/TZYqdnq2KL

[Gwangbin Bae @BaeGwangbin]

Our paper "Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation" will be presented in Session 10 at #ICCV2021.

https://t.co/ttEs5Cdod6

Timeslots:
Oct 13 (Wed) 5-6PM (EDT)
Oct 15 (Fri) 10-11AM (EDT)

w/ @IgnasBud @robertocipolla