Sabitlenmiş Tweet
Luis Piloto
264 posts

Luis Piloto
@EncodeThis
AI + Neuro @DeepMind | Ph.D @PrincetonNeuro | ex @ptoncompmemlab. Opinions my own.
London, England Katılım Mart 2012
1.2K Takip Edilen513 Takipçiler

@vuecinemas Harrow checking in! Apparently, prices are a state secret here. Just two combo options on repeat with no menu. How's a person supposed to know if they're getting fleeced? 🤔 This is cinema 101, folks.

English
Luis Piloto retweetledi

Introducing Gemini 2.5 Pro Experimental! 🎉
Our newest Gemini model has stellar performance across math and science benchmarks. It’s an incredible model for coding and complex reasoning, and it’s #1 on the @lmarena_ai leaderboard by a drastic 40 ELO margin. Only a handful of model releases have leaped ahead so strongly in ELO. 📈
ELO score differences map directly to win rate: e.g. a 400 ELO difference yields a ~91% win rate. Incredible that since 1.5, just a year ago, we jumped 200 ELO (300 since 1.0).
Here’s a fun example where Gemini 2.5 Pro writes code to create an animated swarm of colorful boids swimming in a rotating hexagon. 💫
Try the model for free today in AI Studio. It’s also available to Gemini Advanced users in @geminiapp. aistudio.google.com/app/prompts/ge…
Blog: goo.gle/4c3NitO
English

#CVPR2023 is too much about bold numbers. And it is WAY too easy to cheat on those (few keyboard strokes, right?)
We found two CVPR (orals) that mis-represented their results –– figuring out what to do in regards...
You WILL be found out.
Don't – just don't
English

@karpathy we should call it the halting problem...that's not taken yet, is it?
English
Luis Piloto retweetledi

Our paper, Recursive sequence generation in crows (or Re-crow-sion, my preferred title) is out! Thanks to an awesome team (@KatharinaBrecht, @MillieJohnston_ , A_Nieder), we found that crows join primates in being able to grasp center-embedded sequences. science.org/doi/10.1126/sc…
English

This is great work in this space, congrats to the authors! I do wish I was a reviewer on this as there are some nuances worth unpacking but overall this is really compelling and important work! Wishlist: 1) try object-based models (OP3?) 2) eval models trained on SAYCam data
Luca Weihs@LucaWeihs
(New paper!) Do popular video understanding and embodied models have infant-level physical reasoning abilities? Not as far as we can tell Paper: openreview.net/pdf?id=9NjqD9i… Site: allenai.org/project/inflev…
English

@criticalneuro @alec_helbling @manim_community Omfg Ida. Did you really just explain that to me within the span of a tweet more effectively than hours of (I think JuliaLang-stuffed) IRL presentations??!? With graphical depictions to boot. A-mazing!
English

@EncodeThis @alec_helbling @manim_community TDA:
1- Count holes in the data (in which case a donut and a mug will be the same topology), then
2- for every hole measure across how many scales they endure.
Then the holes-over-scales become signatures of different states in the data. 🤷🏻♀️ 🍩☕️🍺
English

A simple clustering algorithm.
1. Form a graph from a set of points by creating an edge between pairs of points within an epsilon radius.
2. Then label points according to their connected component (the connected subgraph).
Visualization made with @manim_community.
English

@caranha wulfebw.github.io/post/ssb64-rl-… might be able to adapt that to Mario kart 64?
English

@criticalneuro I was wondering why you were up tweeting so late in NYC but obvs you were ✈️. It looks beautiful! Way to make lemonade out of your deadline/vacation collision.
English

@EncodeThis This made my day! Also greetings from my temporary writing desk in an Istanbul hotel, where you’re being cited. deadline and vacation didn’t get along and I’m not mad at it at all!




English

I'm really proud of this work. I'm mega, ultra, jumbo grateful for the support of my collaborators, family, and colleagues to make this project a reality. I hope researchers use our dataset directly and/or engage with more nuanced, specific and psych-inspired benchmarks.
Google DeepMind@GoogleDeepMind
Read more about PLATO in @NatureHumBehav: dpmd.ai/nhb-plato and check out the data set via GitHub: dpmd.ai/github-plato. Work by @EncodeThis, Ari Weinstein, @PeterWBattaglia, and Matt Botvinick. 2/2
English

@criticalneuro Thanks, Ida! Pretty cool you'll be my first citation!!!!
English

@EncodeThis Wow fantastic! And great timing it goes right into my paper before submission :-)
English

@criticalneuro @tyrell_turing @TonyZador @MelMitchell1 @caswellcaswell @ev_fedorenko I am a big fan of Rosa Cao's and Dan Yamin's papers on "Explanatory models in neuroscience." Not sure if they count as hidden gems but happy to give them a shoutout either way :)
English

NeuroAI friends, to make sure I don't miss important citations in a review:
Who coined "neuro_AI" & which papers use it?
What are your favorites *hidden gem* neuro-AI papers?
–not just the most famous reviews!!
@tyrell_turing @TonyZador @MelMitchell1 @caswellcaswell @ev_fedorenko
English


