Call for Blog Posts: Submission deadline: Dec. 1st, 2025 23:59 AOE All information is now available: iclr-blogposts.github.io/2026/about/ Please RT!
Organizers:

@schwinnl.bsky.social @busycalibrating.bsky.social @jonkhler.argmin.xyz @n-gao.bsky.social @mhrnz.bsky.social & myself

See last year's accepted blog posts: iclr-blogposts.github.io/2025/blog/in...

Blog Posts are a great medium to share ML research. If you have new intuitions on past work, noticed key implementation details for reproducibility, have insights into the societal implications of AI, or an interesting negative result consider writing and submitting a blogpost.

📣 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.

A circular diagram with a blue whale icon at the center. The diagram shows 8 interconnected research areas around LLM reasoning represented as colored rectangular boxes arranged in a circular pattern. The areas include: §3 Analysis of Reasoning Chains (central cloud), §4 Scaling of Thoughts (discussing thought length and performance metrics), §5 Long Context Evaluation (focusing on information recall), §6 Faithfulness to Context (examining question answering accuracy), §7 Safety Evaluation (assessing harmful content generation and jailbreak resistance), §8 Language & Culture (exploring moral reasoning and language effects), §9 Relation to Human Processing (comparing cognitive processes), §10 Visual Reasoning (covering ASCII generation capabilities), and §11 Following Token Budget (investigating direct prompting techniques). Arrows connect the sections in a clockwise flow, suggesting an iterative research methodology.

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!