The Computer and Software Engineering Dept. at Polytechnique Montreal is hiring for a tenure-track faculty position in Trustworthy AI! Eligible candidates will be nominated to become affiliated with Mila - Institut québécois d'IA! Link to the official call in the next tweet! Deadline: 8 April

Our recent AAAI paper shows that certain attention heads in transformers are responsible for bias and pruning them improves fairness! In collaboration with Goncalo Mordido, Samira Shabanian , Ioana Baldini, and Sarath Chandar Paper 📰: arxiv.org/pdf/2312.15398…

What is the best way of switching between controllers in Reset Free RL? Read this thread (and come by our poster this Friday morning at ICLR, Hall B) to find out! #ICLR2024 1/n

🚨Is solving complex tasks still challenging for your RL agent? 👑 Subgoal Distillation: A Method to Improve Small Language Agents Paper: arxiv.org/abs/2405.02749 w/ Elias Stengel-Eskin Marc-Alexandre Côté Sarath Chandar

👏👏

Our ACL main paper explains why fairness metrics don't correlate and proposes CAIRO to make them correlate! Extremely grateful to Gonçalo Mordido, Ioana Baldini, and Sarath Chandar! Paper📰:arxiv.org/pdf/2406.05918

Are you a working professional looking to get started with machine learning and AI? I am teaching a 2-day master class in ML foundations in August! This is an ideal training program for doctors, lawyers, policymakers, software engineers, and financial analysts who want to learn

👏👏

🚀 Introducing VisMin arxiv.org/abs/2407.16772 – a benchmark for Visual Minimal Change Understanding! Evaluates VLMs' fine-grained understanding of objects, attributes, relationships, and counting. Code, models & datasets at vismin.net 📷📷[1/13]🧵

If you want to know why fairness metrics don’t agree, and how to make them correlate with CAIRO, come to our ACL poster in Bangkok (room A1) on August 12 from 4:00 pm to 5:30 pm! arxiv.org/abs/2406.05918

Our McGill NLP postdoc Karolina Stanczak receives outstanding thesis award for her PhD work at CopeNLU. Well deserved and congratulations! Grateful to have you in the group. 💐💐💐

With the help of Goncalo Mordido, Samira Shabanian, and my supervisor Sarath Chandar, I am excited to share that I have an accepted paper in Conference on Language Modeling! We show that attending to wider/narrower contexts improves fairness in language models! Paper📰:arxiv.org/pdf/2305.13088

Friends! I am looking for PhD and Masters students to join my group for Fall 2025, Please share with students you may know who are interested in the intersection of language, CogSci, and AI! first deadline is Dec 1st, see my page for more info: evaportelance.github.io/prosstudents.h…

At Chandar Lab, we are happy to announce the second edition of our assistance program to provide feedback for members of communities underrepresented in AI who want to apply to high-profile graduate programs. Want feedback? Details: chandar-lab.github.io/grad-app-help/. Deadline: Nov 15!

I learned a lot from Sarath and highly recommend anyone looking for good supervision to apply :)

In addition to his research, Alex is a great person, and I highly recommend applying :)

Participating and being among the winners of the Speed Science contest at Mila - Institut québécois d'IA was a great experience for me! I learned how to communicate my research ideas and what other Mila researchers are working on!

What's the foundational model for generative chemistry? Our work, BindGPT, is a good candidate, and it will be presented at #AAAI2025 today! We built a simple transformer language model that beats diffusion models by just generating 3D molecules as text! Led by Artem Zholus 1/n

I really enjoyed working with Sarath! This is a great opportunity if you are looking for a post-doc :)

A new paper accepted in Conference on Language Modeling 2025! I led a group of 3 brilliant students to dive deep into the problem of discrimination in language models. We discovered that models that take racist decisions don’t always have biased thoughts!