Waad Ben Kheder

Ph.D in CS

[Waad Ben Kheder @wa3dbk]

Finally ! An Open-Source version of ChatGPT !
Can't wait !
#OpenAssistant #ChatGPT
https://t.co/qJUTBk6Rgx

[Sasha Rush @srush_nlp]

Blog Post (w/ @gail_w): On "Thinking Like Transformers"

In which, I get a bit obsessed with learning how to code in Transformer lang🤖.

https://t.co/Nb6G52vuiK

(You can follow along or do the exercises yourself in a colab notebook.)

[Jürgen Schmidhuber @SchmidhuberAI]

Regarding recent work on more biologically plausible "forward-only" backprop-like methods: in 2021, our VSML net already meta-learned backprop-like learning algorithms running solely in forward-mode - no hardwired derivative calculation! https://t.co/zAZGZcYtmO

[Elon Musk @elonmusk]

🇲🇦🇲🇦 Congrats Morocco!! 🇲🇦🇲🇦

[Charlotte Caucheteux @NeurIPS2025 @c_caucheteux]

🔥Our work has now been accepted to NeurIPS 2022 !!

`Toward a realistic model of speech processing in the brain with self-supervised learning’:
https://t.co/weiGlaiD65

Let’s meet in New Orleans on Tue 29 Nov 2:30pm PST (Hall J #524).

A recap of the 3 main results below 👇

[AK @_akhaliq]

MagicMix: Semantic Mixing with Diffusion Models
abs: https://t.co/ad6ntMsw5Q
project page: https://t.co/HdP673D8qT

[Elon Musk @elonmusk]

the bird is freed

[Sos "Buy Lazy Kickers" Sosowski @Sosowski]

Forget A*, you can easily solve a maze using soft body physics.

[beeple @beeple]

ART BASEL

[Mikel Artetxe @artetxem]

Jonas was an awesome intern and here is the paper that proves it!

Multilingual models are known to suffer from the "curse of multilinguality", which causes performance to drop as they cover more languages. Our new model X-Mod addresses this using language-specific parameters.

[Qiuqiang Kong @QiuqiangK]

Finally accepted! I believe the anonymous reviewers are truly musicology experts!

[. @DenisCosnard]

À quoi ressemblait Paris il y a un siècle ?
À cela !
Images filmées en avril 1920, puis colorisées
https://t.co/FSFnx0WgnX

[Elon Musk @elonmusk]

🚀💫♥️ Yesss!!! ♥️💫🚀

[Dark Web Intelligence @DailyDarkWeb]

Central Bank of #Tunisia hacked by Conti (1560 devices encrypted)

#dailydarkweb #DarkWeb
#darkwebmonitoring #DataBreaches

[Ofir Press @OfirPress]

Since Transformer LMs were invented, we’ve wanted them to be able to read longer inputs during inference than they saw during training. Our Attention with Linear Biases enables this, in very few lines of code, without requiring extra params or runtime https://t.co/GIhnSWvXnh 🧵⬇

[Sara Imari Walker @Sara_Imari]

Thank you Lex for your enthusiasm pushing the boundaries of what we think we know. I really enjoyed our conversation!

[World Health Organization (WHO) @WHO]

FACT: #COVID19 is NOT airborne.

The #coronavirus is mainly transmitted through droplets generated when an infected person coughs, sneezes or speaks.

To protect yourself:
-keep 1m distance from others
-disinfect surfaces frequently
-wash/rub your 👐
-avoid touching your 👀👃👄

[Philippe Etchebest @Chef_Etchebest]

Forcé de réagir face à cette situation
#COVID19france #COVID19 #CORONAVIRUSENFRANCE #CoronavirusFrance

[Waad Ben Kheder @wa3dbk]

Microsoft launches a drag-and-drop machine learning tool #ML #AI #artificialintelligence https://t.co/kOLMMSLwSZ via @techcrunch

[Yann LeCun @ylecun]

I Now call it "self-supervised learning", because "unsupervised" is both a loaded and confusing term.

In self-supervised learning, the system learns to predict part of its input from other parts of it input. In... https://t.co/GpcHEbj5jc