Rohan Sukumaran @ NeurIPS

Grad student @mila_quebec; Responsible AI. Prev: Research Manager @PathCheck_fnd; Applied Research, @SwiggyTech; CSE @IIITSC

[Juan Ramirez @juan43ramirez]

A few more days to submit your COML extended abstract!

[Constrained Learning Workshop @NeurIPS @constrained_ml]

🚨 New Workshop Alert! 🚨

COML @NeurIPSConf 2025 — The first Workshop on Constrained Optimization for Machine Learning is coming to San Diego, Dec 2–7! 🌴

Website: https://t.co/R17UY1wnfY

🧵

[Simon Lacoste-Julien @SimonLacosteJ]

Our NeurIPS workshop proposal was accepted -- please consider submitting your work to it!

[Jose Gallego-Posada @JGallegoPosada]

Meet Cooper — a PyTorch library for constrained optimization in deep learning. 🚀

Cooper makes constraints as easy to use as losses!

@juan43ramirez @meraj_hashemi_ @SimonLacosteJ @Mila_Quebec

💻https://t.co/XU9BT3O63t

🧵👇

[Majdi Hassan @majdi_has]

(1/n)🚨You can train a model solving DFT for any geometry almost without training data!🚨

Introducing Self-Refining Training for Amortized Density Functional Theory — a variational framework for learning a DFT solver that predicts the ground-state solutions for different geometries and generates the training data itself!

🧵

This work is the result of an amazing collaboration with @CristianGabell1 @hatemhelal @dom_beaini @k_neklyudov

📜 Paper: arXiv:2506.01225
💻 Code: https://t.co/f6XjqV7KVa

[Aishwarya Agrawal @aagrawalAA]

My lab’s contributions at #CVPR2025:

-- Organizing @vlms4all workshop (with 2 challenges)
https://t.co/qVVPFugznP

-- 2 main conference papers (1 highlight, 1 poster)
https://t.co/IO3kbIDuwv (highlight)
https://t.co/VGIdty3CTV (poster)

-- 4 workshop papers (2 spotlight talks, 2 posters)
https://t.co/YGkOd446Yl
https://t.co/qVVPFugznP

-- Invited talks and panels: 1 workshop talk, 1 workshop panel, 1 social event panel
https://t.co/FrhQlWAodL
https://t.co/ikiL1lYyx5
https://t.co/fcoOYK947h

-- 6 lab members attending!

See you over the coming days!

I am also looking to hire post-docs, so reach out to me if you are interested at [email protected]

[Alex Hernandez-Garcia @alexhdezgcia]

📣 Call for a postdoc!

We are looking for a postdoctoral researcher to work at the intersection of machine learning and materials science.

Find all details here: https://t.co/odl86ClXRQ

[Hanna Wallach (@hannawallach.bsky.social) @hannawallach]

Exciting news: the Fairness, Accountability, Transparency and Ethics (FATE) group at Microsoft Research NYC is hiring a predoctoral fellow!!! 🎉

https://t.co/gW4jPOba76

[Mandana Samiei @MandanaSamiei]

A great collab with former labmates @AntChen_ & Dongyan! Interesting cognitive limitation in LMs: strong disjunctive bias leads to poor performance on conjunctive causal inference tasks. Mirrors adult human biases—possibly a byproduct of training data priors.

[Rohan Sukumaran @ NeurIPS @rohanalchemist]

@niloofar_mire @CMU_EPP @LTIatCMU @AIatMeta @kamalikac Congrats, Niloofar!!! 🎉🎉🎉

[Niloofar ✈️ icml @niloofar_mire]

📣Thrilled to announce I’ll join Carnegie Mellon University (@CMU_EPP & @LTIatCMU) as an Assistant Professor starting Fall 2026!

Until then, I’ll be a Research Scientist at @AIatMeta FAIR in SF, working with @kamalikac’s amazing team on privacy, security, and reasoning in LLMs!

[Rohan Sukumaran @ NeurIPS @rohanalchemist]

@tremblerz Congrats, Abhishek! This is fantastic news!!!

[Arkil Patel @arkil_patel]

Llamas browsing the web look cute, but they are capable of causing a lot of harm!

Check out our new Web Agents ∩ Safety benchmark: SafeArena!

Paper: https://t.co/De96hmCgSe

[Arkil Patel @arkil_patel]

Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨

Work w/ fantastic advisors @DBahdanau and @sivareddyg

Thread 🧵:

[Reyhane Askari @ReyhaneAskari]

We’re looking for reviewers for our responsible generative AI workshop at CVPR 2025! If you're interested in contributing, sign up here:

[Conference on Language Modeling @COLM_conf]

COLM is looking for senior PhDs to serve as program chair assistants. This requires faculty/mentor nomination. If interested, please ask your advisor to nominate you? Have a student that you think is a great fit? Please nominate them.

Thanks!

https://t.co/B28SUYYh0w

[Avery Ryoo @averyryoo]

Looking for an undergrad volunteer who's interested in SSMs + transformers for neural decoding/BCIs at Mila! Strong coding + Pytorch skills are a must. Please DM/email me your CV + interests (priority given to those based in Montréal). Thanks! 🧠🤖

[Emiliano Penaloza @emilianopp_]

How can we make recommender systems more transparent and controllable without sacrificing quality? Introducing TEARS a scrutable RS that replaces numerical user profiles with editable text summaries (accepted @TheWebConf).

https://t.co/CwoVIRNNnI

1/🧵

[rohan @rohanbanerjeee]

📢New preprint and data alert!
1/ EPISeg: Automated segmentation of the spinal cord on echo planar images using open-access multi-center data
Preprint: https://t.co/tbOfu8Wt0E
Dataset: https://t.co/22NHqWdVLA
More in the thread 🧵

[David Rolnick @david_rolnick]

Internship in our group at @Mila_Quebec in reinforcement learning + graphs for reducing energy use in buildings.

More info and submit an application by Jan 13 here:
https://forms. gle/TCChXnvSAHqzPeMz5
(remove the space - added since Twitter now downweights posts with links)