Jonathan Tompson

Research Scientist at Google

[Tony Zhao @tonyzzhao]

Introducing 𝐀𝐋𝐎𝐇𝐀 𝐔𝐧𝐥𝐞𝐚𝐬𝐡𝐞𝐝 🌋 - Pushing the boundaries of dexterity with low-cost robots and AI. @GoogleDeepMind

Finally got to share some videos after a few months. Robots are fully autonomous filmed in one continuous shot. Enjoy!

[Ayzaan Wahid @ayzwah]

For the past year we've been working on ALOHA Unleashed 🌋 @GoogleDeepmind - pushing the scale and dexterity of tasks on our ALOHA 2 fleet. Here is a thread with some of the coolest videos!

The first task is hanging a shirt on a hanger (autonomous 1x)

[Chelsea Finn @chelseabfinn]

ALOHA 2 is here! 🤖
https://t.co/XuAaaRJqWv

The upgraded hardware has:
* More durability
* Greater fine-grained control
* Lower stress on operator

All off-the-shelf + open-source.

[Tony Zhao @tonyzzhao]

Led by @GoogleDeepMind, we present ALOHA 2 🤙: An Enhanced Low-Cost Hardware for Bimanual Teleoperation.

ALOHA 2 🤙 significantly improves the durability of the original ALOHA 🏖️, enabling fleet-scale data collection on more complex tasks.

As usual, everything is open-sourced!

[Danny Driess @DannyDriess]

What happens when we train the largest vision-language model and add in robot experiences?
The result is PaLM-E 🌴🤖, a 562-billion parameter, general-purpose, embodied visual-language generalist - across robotics, vision, and language.

Website: https://t.co/ouMkeQiGr5

[Eric Jang @ericjang11]

Digit Significance in Machine Learning by Vincent Vanhoucke in @TDataScience https://t.co/MUbLoHAvuV

[ブルーハムハム @THEBLUEHAMHAM]

小さなビートメイカー

[Ofir Nachum @ofirnachum]

A summary of our recent work on the use of convex duality (specifically the use of Q-LP with convex regularization) in RL:
https://t.co/tnJefPsAGJ via @googleai

[Debidatta Dwibedi @debidatta]

This is an awesome explanation of our paper! Especially loved your description of the Temporal Self-similarity Matrix. You end up answering some questions that I was asked during the conference. Thanks for taking the time and effort @ykilcher

[Ilya Kostrikov @ikostrikov]

Welcome to Alphabet!

[koray kavukcuoglu @koraykv]

Welcome @Rob_Fergus to @DeepMind. He's a computer vision and deep learning pioneer & a leading scientist in AI. I’m delighted he’s joined @DeepMind (remaining Prof @ NYU), looking forward to working with him again many years after we were at NYU.

[Google AI @GoogleAI]

Check out RepNet, a single model that analyzes video to provide counting statistics and identify changes in patterns for a broad range of repeating processes—exercising, a bird flapping its wings, pendulums swinging & more. Read more and try it out at https://t.co/lKHepYVOit

[Debidatta Dwibedi @debidatta]

Introducing RepNet, a model that counts repetitions in videos of *any* action

w @yusufaytar, @JonathanTompson, @psermanet and Andrew Zisserman

Paper: https://t.co/PyN7fOu4OU
Project: https://t.co/q9UjEJ8P1P
Video: https://t.co/KvUCduzoOx

#CVPR2020 #computervision #deeplearning

[Ofir Nachum @ofirnachum]

https://t.co/3cHkGgiKvh <-- my most recent paper with @ikostrikov & J. Tompson introducing *ValueDICE* - an off-policy imitation learning alg. We set new SOTA for online imitation learning, and for the 1st time (afaik) beat behavior cloning in the totally offline regime.

[Ofir Nachum @ofirnachum]

@ikostrikov is presenting this at ICLR today! Join our zoom poster session to learn about ValueDICE -- a new & highly-performant off-policy imitation learning algo!
10am-12 & 1-3pm PST.

[Pierre Sermanet @psermanet]

How to scale-up multi-task learning?
Self-supervise plan representations from lots of cheap unlabeled play data (no RL was used).

https://t.co/2ZuuRommNs

by @coreylynch, Mohi Khansari, @xiao_ted, @vikashplus, Jonathan Tompson, @svlevine and @psermanet

[Debidatta Dwibedi @debidatta]

Excited to share our work on self-supervised learning in videos. Our method, temporal cycle-consistency (TCC) learning, looks for similarities across videos to learn useful representations.#CVPR2019 #computervision

Video: https://t.co/NCI6FpsYcj
Webpage: https://t.co/4lMdcDpoPw