Gergely Papp

[Gergely Papp @gergopool]

@MatthewBerman @bot @SpaceXAI Making a family chatbot and a home for family recipes with grok bot :)

[Tim Dettmers @Tim_Dettmers]

QLoRA: 4-bit finetuning of LLMs is here! With it comes Guanaco, a chatbot on a single GPU, achieving 99% ChatGPT performance on the Vicuna benchmark:

Paper: https://t.co/J3Xy195kDD
Code+Demo: https://t.co/SP2FsdXAn5
Samples: https://t.co/q2Nd9cxSrt
Colab: https://t.co/Q49m0IlJHD

[Gergely Papp @gergopool]

@_nateraw

[Gergely Papp @gergopool]

@nucc @ELLISforEurope In some countries, yes. But some countries do allow pursuing a PhD with a BSc. Or at least this is what they say, it looks they don't actually mean it.

[Gergely Papp @gergopool]

@mido_assran This paper to semi-supervised learning is a treasure. Not using labels directly for supervised training, but using them to provide a nice uniform distribution over the predictions instead. Very nice work! I wonder how far representation learning will go in the next few years.

[Asura Technologies @AsuraLPR]

First day @ #MIPS2019 for Asura is a hit! Time and time again it is our live demos of vehicle recognition using make and model recognition and #LPR all integrated into #Milestone XProtect drawing lots of interest and opportunities for new acquaintances. Getting ready for day 2!

[Gergely Papp @gergopool]

Such a multifunctional course from https://t.co/rtRK421Twv!!! If you ever wanted to be the master of deep learning and the rockstar of drawing, @AndrewYNg is your guy! 😉 #DeepLearning #NeuralNetworks

[Arthur Juliani @awjuliani]

Been experimenting with PPO+Curiosity on a more sparse-rewarding environment. Agent has to learn to press the button to spawn a pyramid, then knock the pyramid over to get the (+1 reward) gold brick. Vanilla PPO completely fails. PPO+Curiosity solves it. 🎉

[OpenAI @OpenAI]

Releasing Evolved Policy Gradients, an experimental metalearning technique to let agents rapidly learn to solve novel tasks: https://t.co/UYnBsQXpuZ

[Google DeepMind @GoogleDeepMind]

Kickstarting Deep Reinforcement Learning proposes a paradigm where 'teacher' agents help train 'student' agents. Benefits include faster research cycles and students that can surpass their teachers: https://t.co/QwWd3kxV7B

[Google DeepMind @GoogleDeepMind]

A Generalised Method for Empirical Game Theoretic Analysis: https://t.co/BUDWcet4dq

[Gergely Papp @gergopool]

@awjuliani @mikegeig Could you please tell us the timezone?

[Gergely Papp @gergopool]

My thoughts about possible improvements on #AlphaZero.
#ArtificialIntelligence @DeepMindAI
https://t.co/1sX0e25CxT

[Gergely Papp @gergopool]

@togelius @awjuliani @DeepMindAI @unity3d @Ubisoft @YOKOZUNAdata @theSpiritAI I wish I could afford :’) #studentlife

[Chris (Simpsons artist) @getbentsaggy]

goodbye stephen hawking now that the stars can finally meet you i think that they will be so proud that their atoms created someone quite as special and as brilliant as you xox

[Gergely Papp @gergopool]

My very first blog post. Yay ^^
Here I share my personal experience on #AlphaZero.

https://t.co/1r16XY2lEs

[Pulkit Agrawal @pulkitology]

Do you want to feel as dumb as an RL agent? Try playing this game: https://t.co/ukROIkFuKn where we tried to remove many of the priors that humans typically use. Checkout our paper alongwith @deepakpathak at https://t.co/90SrkYq3Dm

[omoju @omojumiller]

Spread the word fam

This is a remote program and is open to anyone with US work authorization located in US timezones (we’re happy to provide a desk in our San Francisco office if you happen to be located in the Bay Area).

https://t.co/EAP0ziiRu1

[Gergely Papp @gergopool]

I wish I could contribute, very nice job. 🙂
#LCZero #Chess #AlphaZero
https://t.co/d8ghRMYafa

[Eric Jang @ericjang11]

Want some light Friday reading? Here's a short story, "Teacup" about Machine Learning & Generalization. https://t.co/HAVXGKwoJY
🍵