Congrats to Mahan, who is finishing his Master's thesis in beauty with this second paper.

Last week, I gave a talk at Mila - Institut québécois d'IA. The talk should be of interest to anyone working on predictive models, particularly in latent space. In collab. with Mahan Fathi Clement Gehring Jonathan Pilault David Kanaa Pierre-Luc Bacon. See you at ICLR 2026 in 🇦🇹! drive.google.com/file/d/1mQSXFa…

life update: thrilled to announce that i’ll be joining NVIDIA as a research scientist on the alignment team. grateful for the support from mentors and peers. this is a dream come true for both the researcher and the gamer in me!

Introducing our new paper explaining in-context learning through the lens of Occam’s razor, giving a normative account of next-token prediction objectives. This was with Tom Marty Tejas kasetty Léo Gagnon Sarthak Mittal Mahan Fathi Dhanya Sridhar Guillaume Lajoie arxiv.org/abs/2410.14086

In-context learnin (ICL) is one of the most exciting part of the LLM boom. Sequence models (not just LLMs) implement on-the-fly models conditionned on inputs w/o weight updates! Q: are in-context models better than «in-weights» ones? A: some times ICL is better than standard opt.

The talk I gave @ Mila on learning linearized representations of dynamical systems (Koopman representations) is on YouTube. The work was mainly carried out by Mahan Fathi in collaboration with Pierre-Luc Bacon 's lab, and was presented at ICLR 2024. youtube.com/watch?v=wKyN5j…

Llama-Nemotron-v1 technical report is now available on arxiv arxiv.org/pdf/2505.00949…

NeMo RL is now open source! It replaces NeMo-Aligner and is the toolkit we use to post train next generations of our models. Give it a try github.com/NVIDIA/NeMo-RL

Confused about recent LLM RL results where models improve without any ground-truth signal? We were too. Until we looked at the reported numbers of the Pre-RL models and realized they were serverely underreported across papers. We compiled discrepancies in a blog below🧵👇

We're looking for Summer Interns to join the Post-Training Team at @NVIDIA! DM me with your updated resume and three concise bullets detailing your most relevant experience — e.g. publications, repos, blogs, etc. RT please to help us find top talent.

🚀 Nemotron 3 Nano 30B-A3B is here! Open weights + open data + open source. AA Intelligence Index: 52 (Artificial Analysis ) ✅ 1M‑token context ✅ up to 3.3× higher throughput vs similarly sized open models ✅ stronger reasoning/agentic + chat Details + links in the thread 🧵

Nemotron 3 Super is here — 120B total / 12B active, Hybrid SSM Latent MoE, designed for Blackwell. Truly open: permissive license, open data, open training infra. See analysis on Artificial Analysis Details in thread 🧵below:

NVIDIA has released Nemotron 3 Super, a 120B (12B active) open weights reasoning model that scores 36 on the Artificial Analysis Intelligence Index with a hybrid Mamba-Transformer MoE architecture We were given access to this model ahead of launch and evaluated it across

x.com/i/article/2031…