🔥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

Would you like to use Q-learning for LLM fine-tuning? Check out our new preprint where we interpret Q-functions as logits of the LLM: arxiv.org/abs/2505.11081 ✨ Work done with my based colleagues cohere

Later today, Sikata and Marcel will talk about their recent work on oracle-efficient RL with ensembles. Join us!

It's been an incredible experience working on Gemini Diffusion. So much pride in what we've accomplished bringing this from a small research project to an I/O launch

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

Excited to share what I've been up to: Gemini Diffusion is FAST! I'm convinced this will revolutionise iterative workflows: refine, get instant feedback, repeat! So proud of what our small team achieved here🪐

Very excited to share what I have been working on. Having been part of the Gemini Diffusion team since day one, it is amazing to see our model demoed at Google I/O :) sign up below to try it out!

Excited to share what my team has been working on lately - Gemini diffusion! We bring diffusion to language modeling, yielding more power and blazing speeds! 🚀🚀🚀 Gemini diffusion is especially strong at coding. In this example the model generates at 2000 tokens/sec,

Check out our new result on regression with heavy-tailed noise ! I learned a lot on this project, thanks to Mattes Mollenhauer for leading the project. Nic Mücke 🦩 🇪🇺 Arthur Gretton

Finally, we have expert sample complexity bounds in multi agent imitation learning! arxiv.org/pdf/2505.17610 Joint work with Till Freihaut, Volkan Cevher, Matthieu and Giorgia Ramponi

new work on computing distances between stochastic processes **based on sample paths only**! we can now: - learn distances between Markov chains - extract "encoder-decoder" pairs for representation learning - with sample- and computational-complexity guarantees details below 1/n

🚨 New paper accepted at SIMODS! 🚨 “Nonlinear Meta-learning Can Guarantee Faster Rates” arxiv.org/abs/2307.10870 When does meta learning work? Spoiler: generalise to new tasks by overfitting on your training tasks! Here is why: 🧵👇

Dhruv Rohatgi will be giving a lecture on our recent work on comp-stat tradeoffs in next-token prediction at the RL Theory virtual seminar series (RL Theory Virtual Seminars) tomorrow at 2pm EST! Should be a fun talk---come check it out!!

Our new preprint is online ! Structural assumptions on the MDP helps in imitation learning, even if offline :) Joint work with Gergely Neu and Antoine Moulin 😎

Join us tomorrow for Dave's talk! He will present his recent work on randomised exploration, which received an outstanding paper award at ALT 2025 earlier this year.

Meanwhile, excited to be in #Lyon for #COLT2025, with a co-first author paper (arxiv.org/abs/2502.15752) with the amazing team -- Matthew Mallory and our advisor Morgane Austern! Keywords: Gaussian universality, dependent data, convex Gaussian min-max theorem, data augmentation!

Join us for Nneka's presentation tomorrow! Last talk before the summer break.