Research Fellow @ Flatiron Institute - Enhancing sampling with deep generative models
New York, USA
Joined November 2012
- Tweets111
- Following290
- Followers275
- Likes1.3K
Pinned Tweet
Thrilled to share that I successfully defended my PhD last Friday at École Polytechnique! It’s been an incredible journey with my advisor @marylougab and all the amazing researchers I met along the way.
Next chapter: Research Fellow at @FlatironInst in New York, starting Jan 2026
Louis Grenioux retweeted
📣 Our workshop on Emerging Directions in Probabilistic Modeling is next week, Oct 5–7 in NYC!
Full schedule: edpmworkshop.github.io/#sche…
Can't join in person? Talks will be livestreamed on Zoom. Register here: simonsfoundation.zoom.us/web…
📣 We are excited to announce the workshop
Emerging Directions in Probabilistic Modeling: Methods and Scientific Applications
📅 Oct. 5–7, 2026
📍 Flatiron Institute & IBM Research, NYC
Applications are welcome by Aug. 22:
edpmworkshop.github.io
I will be presenting my most recent work "Bridging stochastic flow maps and Boltzmann generators with normalizing flows" (done in collab with @TonyRKOuYang and @hlws_bot) this morning 🙂
Excited to host the generative modeling and sampling workshop next week, with @cdomingoenrich in the beautiful summer of Boston @MSRNE!
(and no regular seminar as last week)
Louis Grenioux retweeted
Excited to host the generative modeling and sampling workshop next week, with @cdomingoenrich in the beautiful summer of Boston @MSRNE!
(and no regular seminar as last week)
Louis Grenioux retweeted
📣 We are excited to announce the workshop
Emerging Directions in Probabilistic Modeling: Methods and Scientific Applications
📅 Oct. 5–7, 2026
📍 Flatiron Institute & IBM Research, NYC
Applications are welcome by Aug. 22:
edpmworkshop.github.io
Fantastic work done in collaboration with @TonyRKOuYang during my visit at @CambridgeMLG. We reformulate learning energy-based diffusion models as solving a classification problem. EBMs are fundamental tools for model composition but also molecular applications.
Can we improve energy-based diffusion models by solving a classification task? 🤔
🚀 Excited to share DiffCLF, accepted at ICML 2026 🇰🇷! ! We predict a sample’s noise level, and recover densities as a by-product.
Joint work with @theh2o64 (co-lead) and @jmhernandez233. [🧵1/n]
Louis Grenioux retweeted
We just brought flow maps to language modeling for one-step sequence generation 💥
Discrete diffusion is not necessary -- continuous flows over one-hot encodings achieve SoTA performance and ≥8.3× faster generation 🔥
We believe this is a major step forward for discrete generative modeling and language modeling alike. 🚀
Full thread from first author @chandavidlee: xitter.cf/chandavidlee/status/20…
Can language models generate high quality full sequences in ONE step?
Yes! Using continuous flows.
We introduce Flow Map Language Models (FMLM) — a fundamentally new approach that outperforms discrete diffusion baselines across the board.
🔥SoTA few-step performance
❤️🔥 ≥8.3× faster sampling
🧵👇
“One-step Language Modeling via Continuous Denoising”
(with amazing coauthors @wognsfjq96 , @mananag_007, Sheel Shah, @jrrhuang, @AdtRaghunathan, @hongseu33, @nmboffi, @jw9730)
Louis Grenioux retweeted
Heads up, NeurIPS attendees! 👋
🚨Don't miss the FPI Workshop (Frontiers of Probabilistic Inference) back again on Dec 7th.
🔉We've curated an incredible set of accepted papers showcasing the future of probabilistic modeling. Schedule & papers: fpineurips.framer.website/
We also have a stellar lineup of invited speakers that should be of broad interest to people in AI4Science
#neurips2025 #ProbabilisticML #AI
Rumours are that there's also a workshop party🫢.
co-organized with a stellar team
@tara_aksa @msalbergo @marylougab @theh2o64 @guanhorng_liu @k_neklyudov Grant Rotskoff @EvaSmorodina @AlexanderTong7
Louis Grenioux retweeted
🚨 Deadline Extension! 🚨
The FPI workshop submission deadline is now August 29th.
Submit your latest research on Probabilistic Inference and Sampling. Don't miss out!
fpineurips.framer.website
#NeurIPS2025 #ProbabilisticInference #AI
📢 Deadline extended!
Submit your work to the Frontiers in Probabilistic Inference workshop by Aug 29 🗓️ (fpineurips.framer.website/).
#NeurIPS2025 #MachineLearning #ProbabilisticInference
1/ Where do Probabilistic Models, Sampling, Deep Learning, and Natural Sciences meet? 🤔 The workshop we’re organizing at #NeurIPS2025!
📢 FPI@NeurIPS 2025: Frontiers in Probabilistic Inference – Learning meets Sampling
Learn more and submit → fpiworkshop.org
Organizers: @tara_aksa @msalbergo @bose_joey @marylougab @theh2o64 @guanhorng_liu Grant Rotskoff @EvaSmorodina @AlexanderTong7
Louis Grenioux retweeted
Working on Probabilistic Inference and Sampling 🤔?
Consider submitting to the FPI workshop at #NeurIPS2025 this year.
🔗fpineurips.framer.website/
🚨Deadline is coming up, and it's Aug 22nd! So submit your best work, early!
Excited to be at SampTA 2025 in Vienna this week! 🇦🇹 If you're around and interested in generative modeling or sampling, let's connect. More about the event: sampta25.univie.ac.at/ – at Vienna, Austria
Louis Grenioux retweeted
1/ Where do Probabilistic Models, Sampling, Deep Learning, and Natural Sciences meet? 🤔 The workshop we’re organizing at #NeurIPS2025!
📢 FPI@NeurIPS 2025: Frontiers in Probabilistic Inference – Learning meets Sampling
Learn more and submit → fpiworkshop.org
Organizers: @tara_aksa @msalbergo @bose_joey @marylougab @theh2o64 @guanhorng_liu Grant Rotskoff @EvaSmorodina @AlexanderTong7
Louis Grenioux retweeted
We’re thrilled to announce the launch of the MolSS Reading Group! 🚀
🔬 MolSS = Machine Learning for Molecular Simulations and Sampling
🔥 First session: June 3rd, 3 PM (UK time) by @jmhernandez233
🗓️ Regular sessions: Every other Tuesday at 4 PM (UK time), 45–60 minutes
Louis Grenioux retweeted
New revision of “BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching” 🚀
(1/6) We introduce NEM and BNEM — diffusion&energy-based neural samplers for Boltzmann distributions.
📝 Read our paper at [arxiv.org/pdf/2409.09787]
Louis Grenioux retweeted
Big congrats to Charles Margossian and Lawrence Saul for winning the #AISTATS 2025 Best Paper Award!
"Variational Inference in Location-Scale Families: Exact Recovery of the Mean and Correlation Matrix"
Louis Grenioux retweeted
Excited to present our work “Denoising Lévy Probabilistic Models” at #ICLR2025 (Thursday 10am)
We extend diffusion models with heavy-tailed noise for better coverage & faster sampling.
Let’s chat about heavy-tailed/discrete diffusion and novel methods!
arxiv.org/abs/2407.18609
Louis Grenioux retweeted
🔥Wanna talk about combining diffusion models and sampling ?🔥
I'll be attending ICLR next week to present my work (main track + FPI workshop) with the one and only @theh2o64, we'll be pleased to discuss about this hot topic. See you there !
Louis Grenioux retweeted
I'll be at ICLR this week, hit me up if you want to discuss diffusion models and guidance!
We'll be presenting arxiv.org/abs/2410.09945 on thu. 24 at the oral session 1C, then in the afternoon at Hall 2B Poster #143. Come say hi!
