iiinova — where your digital self keeps evolving

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 08/06/2026

Tomorrow, Zak will talk about his new deep RL method for hard exploration problems. Join us! The talk will be hosted by Csaba.

052

Reposted by Antoine Moulin

Tim van Erven @timvanerven.nl · 21/04/2026

Summer school on Decisions and Theory for AI! July 13-17 Leiden University Lecturers: Gergely Neu @neu-rips.bsky.social Claire Vernade @claireve.bsky.social Marco Avella Medina Peter Grünwald @petergrunwald.bsky.social Myself Application deadline: April 30 sites.google.com/view/dtailsu...

sites.google.com

DTAIL

Modern AI systems are no longer just engineering artefacts: they are decision-makers operating under uncertainty, constraints, and societal needs. This summer school concerns the intersection of decis...

1104

Reposted by Antoine Moulin

Aaron Roth @aaroth.bsky.social · 09/03/2026

Michael @mkearnsphilly.bsky.social ) and I wrote a blog post about our experiences using AI for research, and our thoughts on what these developments will mean for research, publication, and education: www.amazon.science/blog/how-ai-...

amazon.science

How AI is changing the nature of mathematical research

What machine learning theorists learned using AI agents to generate proofs — and what comes next.

13013

Reposted by Antoine Moulin

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 06/12/2025

So excited for the RL theory meets experiment workshop tomorrow at NeurIPS: arlet-workshop.github.io/neurips2025/... Talks look AMAZING and you can hear me be the foolish experimentalist on a panel

arlet-workshop.github.io

Schedule | ARLET

The session will cover invited talks, contributed talks and posters. The tentative schedule in Pacific Daylight Time (GMT−7) can be found below.

0161

Reposted by Antoine Moulin

Andrew Campbell @arcampbell.bsky.social · 07/10/2025

Very excited to share our preprint: Self-Speculative Masked Diffusions We speed up sampling of masked diffusion models by ~2x by using speculative sampling and a hybrid non-causal / causal transformer arxiv.org/abs/2510.03929 w/ @vdebortoli.bsky.social, Jiaxin Shi, @arnauddoucet.bsky.social

0136

Reposted by Antoine Moulin

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 02/10/2025

We're finally out of stealth: percepta.ai We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us 😀

percepta.ai

Percepta | A General Catalyst Transformation Company

Transforming critical institutions using applied AI. Let's harness the frontier.

711818

Reposted by Antoine Moulin

Sonia Mazelet @soniamazelet.bsky.social · 29/09/2025

I am happy to share that our paper "Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs" was accepted at Neurips 2025 ! 🥳 Huge thanks to my co-authors @rflamary.bsky.social and Bertrand Thirion ! arxiv.org/abs/2506.12025 (1/5)

arxiv.org

Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs

Optimal transport between graphs, based on Gromov-Wasserstein and other extensions, is a powerful tool for comparing and aligning graph structures. However, solving the associated non-convex optimizat...

1305

Reposted by Antoine Moulin

ARLET @arletworkshop.bsky.social · 28/08/2025

News 🎉 We’re thrilled to announce our final panelist: David Silver! Don’t miss David and our amazing lineup of speakers—submit your latest RL work to our NeurIPS workshop. 📅 Extended deadline: Sept 2 (AoE)

042

Reposted by Antoine Moulin

ARLET @arletworkshop.bsky.social · 18/08/2025

We've extended the deadline for our workshop's calls for papers/ideas! Submit your work by August 29 AoE. Instructions on the website: arlet-workshop.github.io/neurips2025/...

arlet-workshop.github.io

Call for Papers | ARLET

A simple, whitespace theme for academics. Based on [*folio](https://github.com/bogoli/-folio) design.

042

Reposted by Antoine Moulin

ARLET @arletworkshop.bsky.social · 05/08/2025

The OpenReview link for our calls (for papers and ideas) is available, submit here: openreview.net/group?id=Neu... We look forward to receiving your submissions!

021

Antoine Moulin @antoine-mln.bsky.social · 28/07/2025

last year's edition was so much fun I'm really looking forward to this one!! join us in San Diego :))

040

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 09/06/2025

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

093

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 02/06/2025

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.

041

Antoine Moulin @antoine-mln.bsky.social · 27/05/2025

new preprint with the amazing @lviano.bsky.social and @neu-rips.bsky.social on offline imitation learning! learned a lot :) when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. lots of open questions left though!

1173

Reposted by Antoine Moulin

Dimitri Meunier @dimitrimeunier.bsky.social · 26/05/2025

🚨 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: 🧵👇

arxiv.org

Nonlinear Meta-Learning Can Guarantee Faster Rates

Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. The main aim of ...

297

Reposted by Antoine Moulin

Dylan Foster 🐢 @djfoster.bsky.social · 26/05/2025

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.bsky.social) tomorrow at 2pm EST! Should be a fun talk---come check it out!!

1105

Reposted by Antoine Moulin

Gergely Neu @neu-rips.bsky.social · 26/05/2025

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 read on for some quick details.. 1/n

13510

Reposted by Antoine Moulin

Ferenc Huszár @inference.vc · 22/05/2025

A new blog post with intuitions behind continuous-time Markov chains, a building block of diffusion language models, like @inceptionlabs.bsky.social's Mercury and Gemini Diffusion. This post touches on different ways of looking at Markov chains, connections to point processes, and more.

inference.vc

Discrete Diffusion: Continuous-Time Markov Chains

A tutorial explaining some key intuitions behind continuous time Markov chains for machine learners interested in discrete diffusion models: alternative representations, connections to point processes...

1215

Reposted by Antoine Moulin

arXiv cs.LG Machine Learning @cslg-bot.bsky.social · 21/05/2025

Mattes Mollenhauer, Nicole M\"ucke, Dimitri Meunier, Arthur Gretton: Regularized least squares learning with heavy-tailed noise is minimax optimal arxiv.org/abs/2505.14214 arxiv.org/pdf/2505.14214 arxiv.org/html/2505.14214

156

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 20/05/2025

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

054

Reposted by Antoine Moulin

Edouard Leurent @eleurent.bsky.social · 20/05/2025

Excited to share what I've been up to: bringing text diffusion to Gemini! Diffusion models are _fast_, and hold immense promise to challenge autoregressive models as the de facto standard for language modeling.

1152

Reposted by Antoine Moulin

Clément Canonne @ccanonne.github.io · 10/05/2025

The tutorials, workshops, and community events for #COLT2025 have been announced! Exciting topics, and impressive slate of speakers and events, on June 30! The workshops have calls for contributions (⏰ May 16, 19, and 25): check them out! learningtheory.org/colt2025/ind...

Community events and tutorials, list from the website

2197

Reposted by Antoine Moulin

Dylan Foster 🐢 @djfoster.bsky.social · 09/05/2025

Announcing the first workshop on Foundations of Post-Training (FoPT) at COLT 2025! 📝 Soliciting abstracts/posters exploring theoretical & practical aspects of post-training and RL with language models! 🗓️ Deadline: May 19, 2025

1165

Reposted by Antoine Moulin

Gergely Neu @neu-rips.bsky.social · 06/05/2025

looking forward to giving a talk at the 2025 GHOST day in the beautiful city of Poznan (Poland) --- hope to see you there this weekend!

161

Reposted by Antoine Moulin

Dylan Foster 🐢 @djfoster.bsky.social · 03/05/2025

Is Best-of-N really the best we can do for language model inference? New paper (appearing at ICML) led by the amazing Audrey Huang (ahahaudrey.bsky.social) with Adam Block, Qinghua Liu, Nan Jiang, and Akshay Krishnamurthy (akshaykr.bsky.social). 1/11

1215

Reposted by Antoine Moulin

Arthur Gretton @arthurgretton.bsky.social · 02/05/2025

Spectral Representation for Causal Estimation with Hidden Confounders at #AISTATS2025 A spectral method for causal effect estimation with hidden confounders, for instrumental variable and proxy causal learning arxiv.org/abs/2407.10448 Haotian Sun, @antoine-mln.bsky.social, Tongzheng Ren, Bo Dai

033

Reposted by Antoine Moulin

Marcel Hussing @marcelhussing.bsky.social · 25/04/2025

We'll be presenting our work on Oracle-Efficient Reinforcement Learning for Max Value Ensembles at the RL theory seminar! Been following this series for a while, super excited we get to present some of our work. 🥳

061

Reposted by Antoine Moulin

Gergely Neu @neu-rips.bsky.social · 23/04/2025

new paper online: "CONFIDENCE SEQUENCES FOR GENERALIZED LINEAR MODELS VIA REGRET ANALYSIS" TL;DR: we reduce the problem of designing tight confidence sets for statistical models to proving the existence of small regret bounds in an online prediction game read on for a quick thread 👀👀👀 1/

2345

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 16/04/2025

Last seminars before the summer break: 04/29: Max Simchowitz (CMU) 05/06: Jeongyeol Kwon (Univ. of Widsconsin-Madison) 05/20: Sikata Sengupta & Marcel Hussing (Univ. of Pennsylvania) 05/27: Dhruv Rohatgi (MIT) 06/03: David Janz (Univ. of Oxford) 06/10: Nneka Okolo (MIT)

0145

Reposted by Antoine Moulin

Claire Vernade @claireve.bsky.social · 08/04/2025

We are organising EWRL in Tübingen in September. We are working on the program and we will soon be able to make first announcements. Stay tuned, follow @ewrl18.bsky.social

02912

Reposted by Antoine Moulin

EWRL @ewrl-org.bsky.social · 08/04/2025

Mark your calendars, EWRL is coming to Tübingen! 📅 When? September 17-19, 2025. More news to come soon, stay tuned!

03714

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 17/03/2025

There is a new RL theory seminar tomorrow ! Join us :)

053

Reposted by Antoine Moulin

Claire Vernade @claireve.bsky.social · 11/03/2025

I’ve put together a short list of opportunities for early career academics willing to come to Europe: www.cvernade.com/miscellaneou... This mostly covers France and Germany for now but I’m willing to extend it. I build on @ellis.eu resources and my own knowledge of these systems.

cvernade.com

Claire Vernade - European career opportunities

European Academic Career Opportunities in 2025

37526

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 10/03/2025

Another week, another super nice RL theory talk! This time with David

031

Reposted by Antoine Moulin

Sam Power @spmontecarlo.bsky.social · 09/03/2025

oh cool news in the red there!

27212

Reposted by Antoine Moulin

Csaba Szepesvari @skiandsolve.bsky.social · 06/03/2025

www.youtube.com/watch?v=9_Pe... An interview with Rich. The humility of Rich is truly inspiring: "There are no authorities in science". I wish people would listen and live by this.

youtube.com

TURING AWARD WINNER Richard S. Sutton in Conversation with Cam Linke | No Authorities in Science

YouTube video by Amii

24013

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 04/03/2025

Today at 6 PM UTC, Dhruv Rohatgi will give a presentation at the RL seminars. Hope to see many of you!

011

Reposted by Antoine Moulin

Arthur Gretton @arthurgretton.bsky.social · 04/03/2025

Video now public from the talk "Learning to act in noisy contexts using deep proxy learning" at the NeurIPS'24 Workshop on Causal Representation Learning! Video: neurips.cc/virtual/2024... Slides: www.gatsby.ucl.ac.uk/~gretton/cou...

185

Reposted by Antoine Moulin

RL Theory Virtual Seminars @rl-theory.bsky.social · 25/02/2025

another week, another LLM and, yes, another RL seminar. join us at 6 PM UTC today!

021

Antoine Moulin @antoine-mln.bsky.social · 20/02/2025

super happy about this preprint! we can *finally* perform efficient exploration and find near-optimal stationary policies in infinite-horizon linear MDPs, and even use it for imitation learning :) working with @neu-rips.bsky.social and @lviano.bsky.social on this was so much fun!!

2232

Antoine Moulin @antoine-mln.bsky.social · 18/02/2025

can Grok 3 prove a lower bound on the bayesian regret though? didn't think so... but Itai can! today at 6 PM UTC

040

Reposted by Antoine Moulin

Ethan Mollick @emollick.bsky.social · 13/01/2025

Most of the talk around AI and energy use refer to an older 2020 estimate of GPT-3 energy consumption, but a more recent paper directly measures energy use of Llama 65B as 3-4 joules per decoded token. So an hour of streaming Netflix is equivalent to 70-90,000 65B tokens. arxiv.org/pdf/2310.03003

818249

Antoine Moulin @antoine-mln.bsky.social · 05/01/2025

just realized 2025 is the year when the Adam paper gets a test of time award and maybe TRPO? what else?

050

Reposted by Antoine Moulin

Jeff Dean @jeffdean.bsky.social · 05/01/2025

Hi folks! I'm excited to be on BlueSky! I'm looking forward to posting about computer science research, ML, scientific advances, tasty food, nature, and making groan-worthy puns.

4547542

Antoine Moulin @antoine-mln.bsky.social · 05/01/2025

We’re back! Join us for the next talks 🤓

030

Reposted by Antoine Moulin

Alexander Terenin @avt.im · 21/12/2024

I'm looking for an emergency reviewer or two for an AISTATS submission in the area of Bayesian ML theory, which at present has the misfortune of three low-quality reviews. If you're able to help, please DM and let me know! Please link your Google Scholar if I don't already know you personally.

123

Antoine Moulin @antoine-mln.bsky.social · 21/12/2024

Yesterday was my last day at Google DeepMind. Interning there when the first GDM Nobel prize, AlphaProof, the Gemini releases and more all happened and having such amazing/ambitious colleagues was quite humbling and really exciting. I look forward to 2025!

191