Chandar Lab

Sarath Chandar's research group at @polymtl, @UMontreal and @Mila_Quebec focusing on Machine Learning!

[Chandar Lab @ChandarLab]

Paper: https://t.co/tRpHNmSFlb
Code: https://t.co/MyFX45iUN7
Project Page: https://t.co/AxiQTKFcR2

[Chandar Lab @ChandarLab]

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.

[Chandar Lab @ChandarLab]

Overall, our results demonstrate that language models can be explicitly trained to behave as better probabilistic samplers, with gains extending well beyond the synthetic distributions used for supervision.

[Artem Zholus @artemZholus]

Extremely excited to share our recent work on diffusion world models. We ask a simple question - what space supports diffusion world modeling the most and how do we evaluate that?Turns out representation is the answer with JEPA space yielding the strongest diffusion world models!

[Nilaksh @nilaksh404]

Diffusion world models can help test and improve robot policies before running them on real robots.

But can the choice of latent space make the WM more faithful?

We show that semantic spaces beat reconstruction spaces on task relevant metrics.

https://t.co/BwHZk7ciUQ

[Chandar Lab @ChandarLab]

Checkout the recent work on diffusion world models from our lab! The work studies a simple but important design choice: should the world model think in pixels reconstruction space or in semantic feature space?

[Nilaksh @nilaksh404]

Diffusion world models can help test and improve robot policies before running them on real robots.

But can the choice of latent space make the WM more faithful?

We show that semantic spaces beat reconstruction spaces on task relevant metrics.

https://t.co/BwHZk7ciUQ

[Ekaterina Lobacheva @KateLobacheva]

Still at #ICLR2026 and interested in training dynamics, simplicity bias, training under data distribution shift, and model merging? Come to our workshop posters to see what we are working on! 🧵👇

[Mehran Shakerinava @MShakerinava]

Want to know the expressivity of Mamba 3?

Come by our ICLR poster!

Sat, Apr 25 • 3:15 PM – 5:45 PM

Pavilion 4 P4-#4409

The Expressive Limits of Diagonal SSMs for State-Tracking

Joint work with Behnoush Khavari, Siamak Ravanbakhsh, and @apsarathchandar.

[Nour Shaheen @nour_shaheen_]

I'm in Rio de Janeiro for ICLR 2026! 🇧🇷

I will be presenting our paper "Is Depth Heterogeneity a Barrier to Model Merging?" (spoiler: not really) at the Workshop for Test-time Updates on Monday April 27th!

Please dm if you're there and you'd like to geek out about... (1/2)

[Chandar Lab @ChandarLab]

Sugar-Shack with our lab!! 🍁🪵

Saying bye bye to a long, harsh winter and hello to sunny days!!☀️🤩

[CoLLAs 2026 @CoLLAs_Conf]

📣 Announcing the CoLLAs Seminars

A year-long exploration of one of the central challenges in AI: building systems that can learn continually, adapt in real time, and improve over their lifetime.

Join us on May 13th at 11 am ET as we kick off the series with Pulkit Agrawal speaking on “Rethinking Post training”.

ℹ️ Learn more: https://t.co/Xs7slVeIYK
✉️ Join our mailing list: https://t.co/m3WvA3EO2E
🔗 Zoom link for the talk: https://t.co/tqRtIEeSf6

[Sarath Chandar @apsarathchandar]

If you work in continual learning, adaptation, online learning, updatable ML, unlearning, model editing and any other form of non-stationary/non-iid learning settings, consider joining the @CoLLAs_Conf mailing list here: https://t.co/RkRNuAdt2A!

[kevin zhang @kevinghstz]

Hierarchical planning unlocks long-horizon, non-greedy behavior in JEPA world models.
Paper: https://t.co/lp5xR5RFnJ
Website: https://t.co/CCFKfmTffk
Code: https://t.co/S3WIFSn2MH

[Sarath Chandar @apsarathchandar]

The abstract deadline for @CoLLAs_Conf is this Friday! If you work in any non I.i.d learning settings, consider submitting to CoLLAs!

[Chandar Lab @ChandarLab]

We're thrilled to see the Workshop on Weight-Space Symmetries coming to #ICML2026! Huge shoutout to our postdoc @KateLobacheva for co-organizing it. We're excited for the ideas and discussions this workshop will bring to the community!

[Weight Space Symmetries @ ICML 2026 @weightsymmetry]

📢Excited to announce the Workshop on Weight-Space Symmetries @icmlconf! We welcome 4-page submissions analysing symmetries, their effects on training and model structure, and practical methods to utilize them.

Submission Deadline: April 24 (23:59 AoE)
#ICML2026