Pierre-Alex
@pierrealexai
Followers
519
Following
373
Media
61
Statuses
222
Curious generalist with a penchant for unconventional ideas. French in SF. RS @GoogleDeepMind , teaching LLMs to be better teachers. Views are my own.
San Francisco 🌉
Joined January 2012
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Edmundo
• 263422 Tweets
CHARLOTTE X TIKTOKLIVE99
• 228971 Tweets
#Narin
• 226687 Tweets
ANILPIN WE ARE THE ONE
• 194506 Tweets
#ปิ่นภักดิ์EP6
• 186729 Tweets
#光る君へ
• 108845 Tweets
KIM TAEHYUNG
• 54227 Tweets
プロジェクトKV
• 53756 Tweets
Zapatero
• 50873 Tweets
東京ドーム
• 39376 Tweets
İdam
• 30738 Tweets
Kostic
• 29906 Tweets
ポルノグラフィティ
• 27650 Tweets
SEVENTEEN AT LOLLAPALOOZA
• 21604 Tweets
NFL Sunday
• 15407 Tweets
ماهر الجازي
• 15325 Tweets
源氏物語
• 15153 Tweets
#降り積もれ孤独な死よ
• 14706 Tweets
LESSONS FROM BIU
• 13654 Tweets
Excited to share our
#ICML2023
paper on Symbolic Regression! We introduce a method that combines a Transformer mutation model with Monte-Carlo Tree Search. We pre-train our model on synthetic example mutations and fine-tune it from online experience. (1/4)
2
25
140
Life update: moved to SF (lower haight) 2 months ago with gf and joined
@GoogleDeepMind
. Excited to make new friends!
ps: who wants a climbing partner (mission cliffs)😬?
2
1
82
The source code for our
#NeurIPS2022
paper "End-to-End Symbolic Regression with Transformers" is available at . Paper available at . Work with
@stephanedascoli
,
@GuillaumeLample
&
@f_charton
.
Come meet us at NeurIPS next week!
2
7
25
Will defend my PhD on "Efficient adaptation of reinforcement learning agents: from model-free exploration to symbolic world models" tomorrow 2pm CET at Meta Paris. If you want to attend in person or hybrid, feel free to DM me!
@mlia_isir
@AIatMeta
2
2
26
Our work on learning exploration strategies without extrinsic rewards was accepted at
@iclr_conf
!
We learn a tree-structured policy that composes skills to reach increasingly far states.
Work with
@jean_tarbou
@alelazaric
@LudovicDenoyer
.
Camera-ready paper coming soon.
Check out our papers accepted at
@iclr_conf
#ICLR2022
!
(2/4) "Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching"
by
@pa_kamienny
,
@jean_tarbou
,
@alelazaric
and
@LudovicDenoyer
In collab w/:
@MetaAI
1
4
14
1
4
20
good time to dust off our work on LLM+MCTS from 1.5y ago on symbolic regression, a program synthesis task whose goal is finding a math equation f s.t. y=f(x)
tldr: pre-train a policy, generate "quality" synthetic data w/ MCTS, finetune π and V, then 🔂
1
3
20
Poster session at 12:05 and 17:10 in room 388-390 for the
#AI4science
workshop.
“Symbolic Model-Based Reinforcement learning” with
@SylvainLamprier
“Privileged Deep Symbolic Regression” with
@BiggioLuca
and Tommaso Bendinelli.
0
4
16
Only in SF do founders spend their Saturday writing and deconstructing a single tweet like a Eminem punchline. Watch out for upcoming cool projects launches 🚀🚀
Launch-a-thon 🚀 with ProductHunt CEO
@rajivayyangar
, General Caralyst
@generalcatalyst
, Alex Riebman
@AlexReibman
and Andrew Cote
@Andercot
🔥
1
6
43
0
2
11
Sharing my experience as a beginner with
#midjourney
: crafting the most personalized and budget-friendly 𝗖𝗵𝗿𝗶𝘀𝘁𝗺𝗮𝘀 𝗴𝗶𝗳𝘁!
Create 🎨, print 🖨️, gift 🎁
Hope to inspire some people and gather feedback. Let's get started!
1
2
6
batman saves your ass in 3sec.
premiere on youtube
with
@abhav_k
@ma_as_
at
@the_builderclub
hackathon
0
1
8
Really cool work👏! Didn’t know about Manim (and that so many YT educators use it), awesome tool! opens up lots of opportunities for generating high-quality videos with more complex mathematical concepts and "story-telling".
6
4
31
1
0
8
generative ai brought to life on canvas
Sharing my experience as a beginner with
#midjourney
: crafting the most personalized and budget-friendly 𝗖𝗵𝗿𝗶𝘀𝘁𝗺𝗮𝘀 𝗴𝗶𝗳𝘁!
Create 🎨, print 🖨️, gift 🎁
Hope to inspire some people and gather feedback. Let's get started!
1
2
6
0
1
7
The approach demonstrates state-of-the-art performance on the SRBench benchmark, showing the potential of combining deep neural models with search abilities for symbolic regression tasks. Work with
@GuillaumeLample
@SLamprier
@MarcoVirgolin
from
@MetaAI
@mlia_isir
@CWInl
0
0
7
At the
@the_builderclub
hackathon, we built Batman 🦸♂️ a life-saving (literally) app. A simple audio record triggers an SOS call, alerting authorities and loved ones to your situation.
real-time demo (Hollywood, call me pls) with
@abhav_k
@ma_as_
0
1
8
How to pre-train deep generative symbolic regression to incorporate priors, e.g. symmetries or appearing sub-expressions.
Work led by Tommaso &
@BggLc
. Visit us at our poster session next Thursday
@icmlconf
! 😚
HF demo:
Code:
@icmlconf
@DouzeDe
@thomenicolas1
@pa_kamienny
@GuillaumeLample
@SLamprier
@MarcoVirgolin
@MetaAI
@CWInl
#ICLM2023
Get ready for
@icmlconf
and read our 8 accepted papers
(4/8) "Controllable Neural Symbolic Regression"
Tommaso Bendinelli,
@BggLc
,
@pa_kamienny
Collab
@MetaAI
,
@CSEMInfo
,
@ETH
2
1
7
0
1
6
Interested in online adaptation in dynamic environments?
Come check our work "Probing Dynamic Environments with Informed Policy Regularization" at
#icml2020
's BIG workshop.
Presentation: Saturday 18th July, 6:15 - 7:30am (PDT), 13:15-14:30 (UTC)
2
3
5
Recent deep neural models have shown competitive performance compared to more classical Genetic Programming algorithms. Unlike GP approaches, they are trained to generate expressions from observations given as context using next-token prediction … (2/4)
1
0
4
Had a fun time creating this modest pic and got me inspired to create some more!
📝 Feedback is more than welcome! tagging some really talented creators for input
@nickfloats
@mechanicmind_ai
@num1crush
@chaseleantj
@iamneubert
@ai_artworkgen
@bri_guy_ai
0
0
3
… however, they usually do not benefit from search abilities, resulting in lower performance on out-of-distribution datasets compared to GP. We use MCTS for planning and fine-tune the mutation and critic models on satisfactory mutations (~ RLHF). (3/4)
1
0
3
𝗭𝗲𝗿𝗼-𝘀𝗵𝗼𝘁.
❌Describing the entire scene in a single prompt failed, likely due to having both the zebra and hippo in it. So did "multi-prompts"
What I wanted: "a zebra reading a book, a hippo drinking wine in a pool, Palm Springs, a Citroen traction car"
🆚
What I got:
1
0
3
𝗙𝗶𝗻𝗮𝗹 𝗿𝗲𝘀𝘂𝗹𝘁!
After upscaling and some magic of my gf on her phone 🪄 Et voilà!
🦓🦛🌴🚗🌤️🌵📙
#midjourney
#MidjourneyAI
#ai
#ChristmasGiftIdeas
1
0
3
if you are i) french, ii) want to learn about European bills, iii) make your mind who to vote for during the next European elections, my friends released a cool tinder-like open-source project,
We created a site to choose your candidate for the European elections.
The twist? It is based on parliamentary votes rather than programs.
Launched it last week, already 40,000 users!
Website :
X account :
@VoteFinder_eu
0
0
1
0
0
4
Work done while interning at
@facebookai
Our new paper "Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization" is now online:
@pa_kamienny
,
@teopir
, Alessandro Lazaric, Thibault Lavril, Nicolas Usunier,
@LudovicDenoyer
0
6
6
0
1
3
anyone with experience in 3d model generation to colab with this future fashion business star?
3
0
11
0
0
4
old thread:
Excited to share our
#ICML2023
paper on Symbolic Regression! We introduce a method that combines a Transformer mutation model with Monte-Carlo Tree Search. We pre-train our model on synthetic example mutations and fine-tune it from online experience. (1/4)
2
25
140
0
0
3
not sure I understand the skepticism around integrating LLMs as part of OS.
like is it that surprising?
isn't what "AI agents" are for?
or maybe the provider (or not getting the deal) is the problem?
0
0
3
Encountered some bumps on my creative journey with
@midjourney
, but here are insights and potential solutions I think could improve the creation experience.
1
0
2
𝗙𝘂𝗻𝗻𝘆 𝗳𝗮𝗶𝗹.
“A man resting on a sunbed” for the lol’z.
@midjourney
where did you get your training data from?😂
1
0
2
Presenting Privileged Information Dropout at 19.45 (UTC+2) for BeTR-RL workshop
@iclr_conf
!
"Privileged Information Dropout in Reinforcement Learning" Pierre-Alexandre Kamienny,
@FeryalMP
,
@kaixhin
,
@WendelinBoehmer
,
@shimon8282
Link:
1
3
7
0
1
2
0
0
1
french politics feeling like game of thrones these days.
extreme right betrayals
1
1
4
really cool! now charlie chaplin with voices pls
We're sharing progress on our video-to-audio (V2A) generative technology. 🎥
It can add sound to silent clips that match the acoustics of the scene, accompany on-screen action, and more.
Here are 4 examples - turn your sound on. 🧵🔊
93
392
2K
0
0
2
0
1
1
Structured decoding.
main idea: leverage priors on model outputs to constrain decoding to a subset of tokens.
guaranteed valid json comes for free (small overhead for creating a finite state machine), and inference might be speeded up.
cool blog:
1
0
2
𝗘𝘅𝘁𝗲𝗻𝗱𝗶𝗻𝗴 𝘁𝗿𝗶𝗮𝗹 𝟯.
• Pan ”a zebra is reading a book on a chair” until its pose is ok
• Improve the costume and sit the zebra on "a chair from 60s"
• Pan again to add "a Citroen traction car"
⚠️ Forced by Midjourney to square the image after each pan
1
0
1
Short version:
ArXiv paper:
0
1
1
0
0
1
𝗧𝗿𝗶𝗮𝗹 𝟭: 𝗘𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁 𝗳𝗶𝗿𝘀𝘁.
• Generate the Palm spring background
• In-paint "a zebra reading a book in a nice costume"
❌Failed
😬Conditioning in-painting by generated images of zebras sitting improved results, but still not enough
1
0
1
when is it useful?
firs things i see are json entries where values can be enumerated or with special types e.g. integers, boolean, as well as for speed-ing up decoding keys. anything else?
i don't yet understand how it can improve on general tasks e.g. summarization?
1
0
2
@shreyaskapur
Nice work 🤌 conditioning the policy model on textual descriptions describing the change would be cool!
Small q: did you find that the value function learned using edit distance between target and current programs generalized to drawn images? or maybe you trained on drawings?
0
0
0
𝗚𝗲𝘁𝘁𝗶𝗻𝗴 𝘀𝘁𝗮𝗿𝘁𝗲𝗱.
⏱️In 5 minutes, you can subscribe to Midjourney ($30/ mo) 💸 and get impressive results using basic features (generation, upscaling, in-painting)
For instance, “classy zebras reading in a palm spring house” yields the following image:
1
0
1
@tianyi_zhou12
@DeqingFu
@robinomial
I wonder if this is similar to what we observed in this symbolic regression work.
Our model is trained on a vast dataset of synthetic examples, and scales to input dimensions up to ten. After several million examples, the attention maps start to reveal intricate mathematical analysis : in the example f(x)=sin(x)/x below, we see Fourier-like patterns. 4/4
0
0
5
0
0
1
𝗙𝗶𝗻𝗮𝗹 𝗽𝗼𝗹𝗶𝘀𝗵.
• Improve quality : notice how the sky got darker due to image squaring?
➡️In-paint the sky, careful not to erase pixels from the hippo
• Adjust last details : palm trees, cactus and costume colors and car grille
1
0
1
@rakesh_goyal
shame we did not ship Batman in time...
At the
@the_builderclub
hackathon, we built Batman 🦸♂️ a life-saving (literally) app. A simple audio record triggers an SOS call, alerting authorities and loved ones to your situation.
real-time demo (Hollywood, call me pls) with
@abhav_k
@ma_as_
0
1
8
0
0
1
@justinsunyt
@MultiOn_AI
whats up with the scrolls? are you using screenshots or something? (if so how do you avoid having the chat box on the screenshots?)
use any multimodal model to match with unstructured html?
thanks!
1
0
1
@giansegato
hey would love to meet, enjoyed reading your experience on moving to the us/getting married etc... as I was going over this a year later 🫡
1
0
1
as models become better at following instructions, what is the future for structured decoding?
i only see the inference speedup?
also, is there a cost to merging tokens (distribution shift)?
1
0
1
𝗧𝗿𝗶𝗮𝗹 𝟯: 𝗛𝗮𝗿𝗱 𝗰𝗼𝗺𝗲𝘀 𝗳𝗶𝗿𝘀𝘁.
• Generate “A feminine hippo on a pool mattress, drinking wine in a pool, Palm Springs house”
• In-paint the hippo in “an orange pool ring” then improve her “arms resting on the ring"
👌 Final result
1
0
1
Prompting.
is json mode just prompting the model to output a json, giving the json schema as input and json.load'ing the response?
is there 1 or 2 model calls. if 1, has anyone studied the difference in performance by not allowing model to "think"?
1
0
2
𝗜𝗺𝗽𝗿𝗼𝘃𝗶𝗻𝗴 𝗶𝗻-𝗽𝗮𝗶𝗻𝘁𝗶𝗻𝗴.
Generation quality 📉 with larger images, especially as in-painting surface📉. Attention mechanism struggles with out-of-domain prompts eg "a monkey sitting on a lion's head" & too many elements.
💡Manual Attention Region Specification
1
0
1
These were first ideas I had when doing my first
#midjourney
project, which I highlighted here . Curious to see if the community has developed any of these or if you've got some cool tips to share!
Sharing my experience as a beginner with
#midjourney
: crafting the most personalized and budget-friendly 𝗖𝗵𝗿𝗶𝘀𝘁𝗺𝗮𝘀 𝗴𝗶𝗳𝘁!
Create 🎨, print 🖨️, gift 🎁
Hope to inspire some people and gather feedback. Let's get started!
1
2
6
0
0
1
𝗦𝘂𝗿𝗽𝗿𝗶𝘀𝗶𝗻𝗴 𝗺𝘆 𝗾𝘂𝗶𝗿𝗸𝘆 𝗴𝗳'𝘀 𝗳𝗮𝗺𝗶𝗹𝘆!
Each member is represented by a distinctive animal. Dad: 🦓, mom: 🦛
Their interests can be summed up in the goal prompt:
"a zebra reading a book, a hippo drinking wine in a pool, Palm Springs, a Citroën Traction car”
1
0
0
are libraries like instructor, llama_index, ... mainly wrapping json mode by abstracting jsons w/ clean pydantic objects? they also seem super useful to catch validation error traces to do recursive calls. anything else?
2
0
2
𝗧𝗿𝗶𝗮𝗹 𝟮: 𝗭𝗼𝗼𝗺-𝗼𝘂𝘁 (𝗭𝗢) & 𝗣𝗮𝗻.
• Generate “Zebra reading, Palm Springs, car”
• ZOs and Pans with “a hippo drinking wine in a pool” and “a Bull Terrier dog”
✅ Better thanks to large in-painting spaces
⚠️ Abusing ZOs and Pans disrupts the composition
1
0
1