📣 Call for Blog Posts at #ICLR2026 @iclr_conf Following the success of the past iterations, we are opening the Call for Blog Posts 2026! iclr-blogposts.github.io/2026/about/#... Please retweet!

Fantastic opportunity to join our team at the European Center for Medium-Range Weather Forecast (ECMWF) as an ML Scientist working on Atmospheric Composition/Air Quality Forecasting: <https://jobs.ecmwf.int/Job/JobDetail?JobId=10318> Write me if you have any questions!

If you are at @iclr-conf.bsky.social and are interested in making your RLHF really fast come find @mnoukhov.bsky.social and me at poster #582.

I am at ICLR this year, please reach out if you would like to have a chat.

Models like DeepSeek-R1 🐋 mark a fundamental shift in how LLMs approach complex problems. In our preprint on R1 Thoughtology, we study R1’s reasoning chains across a variety of tasks; investigating its capabilities, limitations, and behaviour. 🔗: mcgill-nlp.github.io/thoughtology/

Our work on Asynchronous RLHF was accepted to #ICLR2025 ! (I was so excited to announce it, I forgot to say I was excited) Used by @ai2.bsky.social for OLMo-2 32B 🔥 New results show ~70% speedups for LLM + RL math and reasoning 🧠 🧵below or hear my DLCT talk online on March 28!

Thanks again to my collaborators: @vwxyzjn.bsky.social @sophie-xhonneux.bsky.social @arianh.bsky.social Rishabh and Aaron who have not yet migrated 🦋 DMs open📲let's chat about about everything LLM + RL @ ICLR and check out Paper 📰 arxiv.org/abs/2410.18252 Code 🧑‍💻 github.com/mnoukhov/asy...

Come to our Spotlight Poster #4702! East Exhibition Hall A-C

Voici un résumé d'une minute de l'article de @sophie-xhonneux.bsky.social " Efficient Adversarial Training in LLMs with Continuous Attacks ". Venez voir le poster vedette à @neuripsconf.bsky.social aujourd'hui : Session de posters 3 Est, #4702.

I will be at NeurIPS! Would love to chat about research! Especially about fine-tuning of LLMs as well as generative models more generally and reasoning! I will be presenting "Efficient Adversarial Training in LLMs with Continuous Attacks" (spotlight) at the morning poster session on Thursday!