🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I just got my copy. It’s a good book and fills a unique and valuable niche, namely a code-first / pragmatic approach to causal inference using ML tools like DoWhy and Pyro.

Had a great time at khipu.ai in Santiago, Chile. My talk on Sequential decision making using online variational bayes is here, in case you are interested. (Lots of other cool talks online too) youtube.com/live/s9VJv0GQE…

Gemma 3 is best in class for a VLM that runs on 1 GPU. Should make RL fine tuning feasible. Also Academic researchers can apply for Google Cloud credits (worth $10,000 per award) to accelerate their Gemma 3-based research.

Our BONE paper has been accepted to TMLR. It derives methods for state space inference in non stationary environments, where changes to the DHO can be gradual (eg drift) or sudden (eg change point)

I'm happy to announce that v2 of my RL tutorial is now online. I added a new chapter on multi-agent RL, and improved the sections on 'RL as inference' and 'RL+LLMs' (although latter is still WIP), fixed some typos, etc. arxiv.org/abs/2412.05265…

I am pleased to announce that the paper on our Dynamax Jax library for SSMs is now available at joss.theoj.org/papers/10.2110…. Code is at github.com/probml/dynamax/. Joint work with Scott Linderman Gerardo Duran-Martin ᴘᴇᴛᴇʀ ɢ. ᴄʜᴀɴɢ Aleyna Kara Giles HarperDonnelly Xinglong

I am pleased to announce that I have updated the online versions of my 2 textbooks (see probml.github.io/pml-book/): I fixed all issues listed on github, added some new references (esp on LLMs), and made a few other small tweaks.

I had a great time diving at Wakatobi Dive Resort in Indonesia (although unfortunately I got an ear infection and had to skip the last couple of days). Tomorrow off to Singapore for #ICLR2025 (DM me if you want to meet).

I dont know why singapore air is rated number 1 in world. their business class beds are much less comfortable than united/ polaris, because they are narrow and not straight. Food is good but not amazing. IMHO Emirates is best, then KLM & United (but grateful not economy class :)

This was a great talk (*) on using (proper multi-turn) RL for training LLM agents to reason and use tools. Very bullish on this "Generative Agents" direction! (* Audio was very bad; fortunately brains are good at source separation :)

I am pleased to announce a new version of my RL tutorial. Major update to the LLM chapter (eg DPO, GRPO, thinking), minor updates to the MARL and MBRL chapters and various sections (eg offline RL, DPG, etc). Enjoy! arxiv.org/abs/2412.05265

Does anyone know if ChatGPT keeps some kind of context or user profile across sessions? If i ask it to derive mathy things related to online Bayes, it often asks me if I want to see a low-rank version of it, or a Thompson sampling version. How does it know I care? Spooky.

100%.

Great article.

I think it's quite misleading for the big labs to be promoting how well their VLMs work on pokemon, given how much (game-specific) manual annotation is required behind the scenes. Solving general tasks from pixel input is much harder than coding ("Moravec's revenge").

Well, it seems that the Elon / Trump bromance is finally over, as I predicted… 🍿

This is a very thought provoking interview with my former student. I do think AI personas (esp multimodal and real time) may be addictive and seem better than humans - but so is heroin (albeit heroin has less useful applications than AI).