Glad to be in Washington with Alex Ostapenko to present at the continual-causality bridge programme at #AAAI23. Do not hesitate to send me pm if you want to have a chat :)

We are glad to announce that our paper: "Challenging Common Assumptions about Catastrophic Forgetting" co-authored with Alex Ostapenko, @__z__9, Md Rifat Arefin, Pau Rodríguez , Laurent Charlin , Irina Rish has been accepted to @Collas2023. (arXiv arxiv.org/abs/2207.04543) [A thread (1/N)]

Ditch the traditional single-distribution learning and soak up some fresh perspectives in Montreal this summer! 🌞Join us at #CoLLAs2023 from August 22 to 25. See you where non-i.i.d. learning meets poutine! 🧠🍟 Register here: lifelong-ml.cc

You can't spell 'Continual Learning' without 'Rahaf Aljundi' Rahaf Aljundi. Okay, maybe you can, but why would you want to? 😜 Don't miss the chance to see her at #CoLLAs2023 in Montreal! Register now: lifelong-ml.cc

Bing Liu wrote the book on Lifelong Machine Learning. That's not a metaphor, folks. It's the closest thing we have to a sacred text! 📖 Join us at #CoLLAs2023 and get schooled by the master himself! 🧠 Register here: lifelong-ml.cc"

Starting the train journey to NeurIPS Conference with Alex Ostapenko from white Montréal and Québec! First stop: New York #SlowTravel

Just 32 train-hours away from New Orleans & NeurIPS Conference ! It's gonna be fun with this Mila - Institut québécois d'IA gang :) Léna Néhale Ezzine Julia Kaltenborn Alex Ostapenko Arthur Ouaknine Julien Boussard

The ML community has been calling for a large scale climate dataset. In our recent Neurips 2023 publication, we introduce ClimateSet: A ➡️ large-scale ➡️ consistent ➡️ ML-accessible climate model dataset 🌍. 1/8 arxiv.org/abs/2311.03721 climateset.github.io

Happy to share the preprint of my MSR intern project: Guiding Language Model Reasoning with Planning Tokens (arxiv.org/abs/2310.05707). We propose to insert tunable special planning tokens in front of each chain-of-thought step to guide the generation of the actual reasoning step.

🚨 Open-source AI community - stop building everything from scratch, let's build on each other's (and your own) work over time - continually, as we should! Don't waste previoius compute and human effort! See arxiv.org/abs/2403.08763 - simple & useful tips on how to just keep

paper page: buff.ly/3KavOyB

Join us at the #CVPR2025 Workshop on #ContinualLearning in #ComputerVision the 18th of June in Seattle🌳! Plenty of chances of networking and an exciting program for you!🎊 🔗sites.google.com/view/clvision2… 🧵(1/4)

Adhering to the claimed values is a true test of commitment, not everyone has courage to pass it. Signed Montreal responsible AI declaration? Consider signing the open letter against the use of military AI technologies in Gaza and the occupied West Bank: forms.gle/x2BbKiuwvZKcnH…

Mila's annual supervision request process opens on October 15 to receive MSc and PhD applications for Fall 2025 admission! Join our community! More information here mila.quebec/en/prospective…

Be part of Mila - Institut québécois d'IA and join the world’s largest community of academic researchers in deep learning. Submit your supervision request today

🚨 New agent framework! 🚨 My team at ServiceNow Research is releasing TapeAgents: a holistic framework for agent development and optimization. At its core is the tape: a structured agent log. Repo: github.com/ServiceNow/Tap… Paper: servicenow.com/research/TapeA… Why you should care: 🧵

Introducing a framework for end-to-end discovery of data structures—no predefined algorithms or hand-tuning needed. Work led by Omar Salemohamed. More details below. arxiv.org/abs/2411.03253

We’re really excited to release this large collaborative work for unifying web agent benchmarks under the same roof. In this TMLR paper, we dive in-depth into #BrowserGym and #AgentLab. We also present some unexpected performances from Claude 3.5-Sonnet

Exciting release from ServiceNow Research — introducing Apriel-5B, a compact and efficient open-source language model that targets the sweet spot between capability and efficiency.

🚨🤯 Today Jensen Huang announced SLAM Lab's newest model on the ServiceNow Events stage: Apriel‑Nemotron‑15B‑Thinker 🚨 A lean, mean reasoning machine punching way above its weight class 👊 Built by SLAM × NVIDIA. Smaller models, bigger impact. 🧵👇