Anabel @AnabelCluster

Mila is the best! Great environment, best supervisors, and amazing colleagues!

Mila - Institut québécois d'IA @Mila_Quebec

2 weeks ago

Mila's annual supervision request process is now open to receive MSc and PhD applications for Fall 2027 admission! For more information, visit mila.quebec/en/prospective…

3 56 176 120K 165

Mila's annual supervision request process is now open to receive MSc and PhD applications for Fall 2027 admission! For more information, visit mila.quebec/en/prospective…

Introducing RoboJEPA, the first scaling law for multiembodiment world models. We scaled JEPA predictors up to 8B params, showed scaling laws extrapolate and correlated compute scaling with planning performance. We release all checkpoints and the code. robojepa.github.io

We (@ChandarLab) are continuing our tradition of helping underrepresented students apply for grad school by reviewing their application materials and giving feedback! Please retweet this for maximum reach! Deadline Nov 1st!

Chandar Lab @ChandarLab

4 weeks ago

🎓 Graduate Program Application Mentorship Applying to grad school doesn't have to be overwhelming! Get personalized 1:1 support from students who’ve successfully navigated the process. 🔗 Apply now: forms.gle/FyjEuLmjcdREF3… 🗓️ Deadline: Nov 1, 2026 👇 Here is what you get:

1 14 55 13K 58

GRRREAT Opportunity! Something you shouldn't miss! Do apply!

Chandar Lab @ChandarLab

4 weeks ago

🎓 Graduate Program Application Mentorship Applying to grad school doesn't have to be overwhelming! Get personalized 1:1 support from students who’ve successfully navigated the process. 🔗 Apply now: forms.gle/FyjEuLmjcdREF3… 🗓️ Deadline: Nov 1, 2026 👇 Here is what you get:

1 14 55 13K 58

🎓 Graduate Program Application Mentorship Applying to grad school doesn't have to be overwhelming! Get personalized 1:1 support from students who’ve successfully navigated the process. 🔗 Apply now: forms.gle/FyjEuLmjcdREF3… 🗓️ Deadline: Nov 1, 2026 👇 Here is what you get:

🎉 Thrilled to share that 8 papers from our lab (and collaborations with lab members) have been accepted at #NeurIPS2026! The work spans RL, world models, dynamical systems, LLM safety & interpretability, tabular foundation models, and forecasting. Huge congrats to everyone 🧵👇

Simple ideas often generalize best! Loss smoothing is one of those really simple ideas that works surprisingly well for adaptation under distribution shift. Really excited about this line of work!

Continual RL Workshop @continual_learn

2 months ago

Our third invited talk by Sarath Chandar (@apsarathchandar) was about: 🎙️ Stable Adaptation Under Distribution Shift 🎥 youtube.com/watch?v=eddBBY…

0 1 28 7K 14

Turns out that many contemporary LLMs still struggle to explain probabilities and uncertainty in plain natural language 👀

Congratulations!

Nour Shaheen @nour_shaheen_

3 months ago

I am pleased to share that I successfully defended my master's thesis at @polymtl and @Mila_Quebec , titled: "Understanding Out-of-Distribution Generalization in Tabular In-Context Learning". I passed with distinction and was nominated for the best Msc thesis award.

keyboard_arrow_left Previous keyboard_arrow_right Next

2 3 24 3K 2

The goal of this program is to identify under represented students from very early stage (high school) and introduce them to CS and programming! I’m super proud of this initiative that is getting mature over the last 3 years!

Chandar Lab @ChandarLab

3 months ago

For the third year in a row, we held our annual Highschool Internship for recent graduates from across Montreal! 🎓🎉💻 Ten bright students underwent a month-long summer school and got introduced & coached on the basics of computer science and programming!

1 8 26 5K 0

For the third year in a row, we held our annual Highschool Internship for recent graduates from across Montreal! 🎓🎉💻 Ten bright students underwent a month-long summer school and got introduced & coached on the basics of computer science and programming!

@ChandarLab will be at #ICML 2026 in Seoul — South Korea 🇰🇷 !! Presenting our most recent state-of-the-art research on continual learning, reinforcement learning and AI agents! Drop by and check it out! 🔥

Excited to share our latest work: Loss Smoothing for Stable Adaptation Under Distribution Shift. TL;DR: When adapting a model, don’t abruptly switch to the new objective. Gradually smooth the transition from the old objective to the new one. Preprint: arxiv.org/abs/2607.00634 🧵 1/n

We are super excited to announce @ChandarLab 7th Annual Research Symposium! 🔥 Join us on July 23–24 for two days of talks on deep learning, NLP, reinforcement learning, continual learning, and AI for science, plus a keynote by @mengyer from NYU! Event is hybrid!

📅 Submit by July 17 🦞

New paper from the lab: Ask a base LLM to pick a random weekday, and it might output "Wednesday" 80% of the time. We show that this can be fixed and that probabilistic calibration is actually a trainable capability.

Congratulations Pranshu!!!

Pranshu Malviya @pranshumalviya8

6 months ago

Defended my thesis today! PhD 🎓 ✅ Huge thanks to my supervisor @apsarathchandar, collaborators and everyone who helped me along the way! @ChandarLab @Mila_Quebec @polymtl

6 2 56 10K 0

A message from the Rome Champion! 📣 @ElinaSvitolina | #IBI26

Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/