Nikhil Agarwal

Graduate Researcher at Interactive Robotics Lab @ ASU

[OpenAI @OpenAI]

We’re releasing Triton 1.0, an open-source Python-like programming language for writing efficient GPU code. OpenAI researchers with no GPU programming experience have used Triton to produce kernels that are 2x faster than their PyTorch equivalents. https://t.co/bdovUjTMuF

[Lilian Weng @lilianweng]

Diffusion models are another type of generative models, besides GAN, VAE, and flow models. The idea is quite smart and clean. It is flexible enough to model any complex distribution while remains tractable to evaluate the distribution.

https://t.co/3eaekDiUOU

[Heni Ben Amor @asurobot]

Only a couple hours to our ICRA 2021 workshop "Towards Curious Robots"! Invited talks by Josh Tenenbaum, Sid Srinivasa, Leyla Takayama, Pierre-Yves Oudeyer, Nick Roy and Kostas Daniilidis. Please join us, Friday 9am EDT 🥳[website] https://t.co/jcnvRQuC9N

[Google DeepMind @GoogleDeepMind]

Introducing AndroidEnv, an open-ended platform for training agents on Android apps and games. With a universal touchscreen interface, access to the entire OS, and a number of ready-to-use tasks, AndroidEnv is a promising domain for RL research: https://t.co/MZIYOwxlnT

[Clarissa Ward @clarissaward]

Please watch our story on the heartbreaking and horrifying tragedy taking place in India right now #IndiaCovidCrisis

[Sergey Tulyakov @SergeyTulyakov]

1/4. Exciting news! The code for our #CVPR2021 work for animating articulated objects is available. With just a single image and a driving video, your favorite characters, historical figures now can tell their stories!
#animation #machinelearning #DeepLearning

[Sitara Parker @Sitara_Parker]

The moral compass of India has spoken. The final word.

https://t.co/GWVUfoaCuK

[Jay Alammar @JayAlammar]

Presenting the Explainable AI Cheat Sheet:

Video: https://t.co/zybCMspzzC
Cheat Sheet: https://t.co/AN28pbBqpd

A high-level map to major categories of ML Explainability. Informed by excellent work by @ChristophMolnar @IAugenstein @sameer_ and others. Plenty of links!

[Heni Ben Amor @asurobot]

I will organize an ICRA 2021 workshop entitled "Towards Curious Robots: Approaches for Intrinsically-Motivated Intelligent Behavior". Thanks to Honda Research USA, an Nvidia RTX 3090 GPU will be awarded to the "Best Poster"! Please consider submitting: https://t.co/UKbnO2BqPv

[Jeff Clune @jeffclune]

Thrilled to share that "First return, then explore" appears today in Nature! Go-Explore solves all unsolved Atari games*, ending a long quest by the field that began in Nature. Led by @AdrienLE & @Joost_Huizinga w @joelbot3000 @kenneth0stanley & myself. https://t.co/X9RIN5pQC3
1/

[Google DeepMind @GoogleDeepMind]

DreamerV2, a collaboration between DeepMind, @GoogleAI and the @UofT, is the first RL agent based on a world model to achieve human-level performance on the Atari benchmark. Read more ⬇️

[Phil Long @philipmlong]

New paper with @niladrichat and Peter Bartlett called "When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?": https://t.co/NVEE7F0WtC.

[AI at Meta @AIatMeta]

Facebook's AI Residency program, which gives residents 12 months of practical experience in AI working with leading researchers, is accepting applications until January 31st! Please apply today: https://t.co/i1lQAmENQP

[George Mack @george__mack]

THREAD: 15 of the most useful razors and rules I've found.

Rules of thumb that simplify decisions.

[Tom Zahavy @TZahavy]

Excited that our paper "Discovering a set of policies for the worst case reward" was accepted to #ICLR2021 as a spotlight!

We present a policy iteration algorithm that discovers meaningful behaviours in the no-reward setting by maximising robustness!

https://t.co/LigxMoN6As

[kwai 葵花 🌻 🇭🇰 @kwaiflower]

A personal comic to end 2020 (1/3)

[Ankur Handa @ankurhandos]

Some simulation platforms that caught my eye this year 🧵

[Heni Ben Amor @asurobot]

Want to teach your robot new tricks with NLP and Deep Learning? We are posting the full source-code to our NeurIPS 2020 paper along with an easy, hands-on tutorial on Medium - lots of explanations and videos!
Github Code: https://t.co/D8BUvxvemt
Medium: https://t.co/1FiIWtQl6d

[Leonardo DiCaprio @LeoDiCaprio]

#DefundBolsonaro #AmazonOrBolsonaro #WhichSideAreYouOn

[The Daily Show @TheDailyShow]

Why did Rayshard Brooks have to lose his life?