🔥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

Introducing NeuralOperator 1.0: a Python library that aims at democratizing neural operators for scientific applications by providing all the tools for learning neural operators in PyTorch : state-of-the-art models, built-in trainers for quick starting and modular neural operator

This release was long in the making and the result of a large group effort. Check out our white paper: arxiv.org/abs/2412.10354 With Zongyi Li, Nikola Kovachki, David Pitt, Miguel Liu-Schiaffini, @Robertljg, Boris Bonev, Kamyar Azizzadenesheli, Julius Berner and Prof. Anima Anandkumar

📢 Internship opportunities in our Fundamental Generative AI Research Group (research.nvidia.com/labs/genair) at NVIDIA!

Happy to share our latest work on #diffusion models without data: building theoretical bridges between existing methods, analysing their continuous-time asymptotics, and showing some cool practical implications. arxiv.org/abs/2501.06148 #MachineLearning 1/9

Happy to share one of my last works! If you are interested in diffusion samplers, please take a look🙃! Many thanks for all my colleagues for their intensive work and fruitful collaboration, especially for malkin1729 for leading this project! Stay tuned for the future ones!

Our new work arxiv.org/pdf/2501.06148 studies connections between discrete and continuous time diffusion samplers - after all, most things are very much related (GFlowNets, optimal control, path measures, PDEs). This allows us to reach faster convergence by randomized time steps.

I'm happy to say that SCLD has been accepted at ICLR25!

Thrilled to announce our paper "Robust Representation Consistency Model (rRCM)" was accepted to #ICLR2025. It combines contrastive learning with consistency training to enhance robust representation learning and sets a new standard in certified robustness. Jiachen Lei Julius Berner

Arnaud Doucet Shreyas Padhy check our maintained list for neural samplers 😃 github.com/J-zin/Awesome-…

We are hiring an intern on generative models for proteins for 6-12 months and typically results in publication. Find out what science is like in a bio-ml industry research lab. Bonus: float along the Rhine to work (perfectly normal commute here):tinyurl.com/3x7ef6z5

Thanks for the kind words Arnaud Doucet ! I wanted to shout-out some other great work in the same vein as us - arxiv.org/abs/2501.06148 (Julius Berner @ICLR‘25, Lorenz Richter, Marcin Sendera et al) arxiv.org/abs/2410.02711 (Michael Albergo @ICLR2025 et al) arxiv.org/abs/2412.07081 (Junhua Chen et al)

Our new work arxiv.org/pdf/2503.01006 extends the theory of diffusion bridges to degenerate noise settings, including underdamped Langevin dynamics (with Denis Blessing, Julius Berner). This enables more efficient diffusion-based sampling with substantially fewer discretization steps.

Reach out if you’re also at #ICLR25 and drop by our posters: 1️⃣Diffusion samplers & SMC: x.com/julberner/stat… 2️⃣Contrastive learning & consistency models: x.com/animaanandkuma… 3️⃣Underdamped diffusions (also come to our oral at the FPI workshop): x.com/lorenz_richter…

🔥📔 This week at #ICLR2025, our fundamental generative AI research team (GenAIR) is (co-)presenting 11 papers, 6 of which were developed or led primarily by our team members. Below, I am listing our main papers with a one-sentence summary.

🔥 I'm at ICLR'25 in Singapore this week - happy to chat! 📜 With wonderful co-authors, I'm co-presenting 4 main conference papers and 3 GEMBio Workshop papers (gembio.ai), and I contribute to a panel (synthetic-data-iclr.github.io). 🧵 Overview in thread. (1/n)

FPI workshop off to a great start with Emtiyaz Khan talking about Adaptive Bayesian Intelligence! Come check it out in Peridot 202-203 #FPIWorkshop #ICLR25

Francisco Vargas and Michael Albergo with a combined talk on sampling inference and transport at #FPIworkshop.

Excited to introduce our latest work, Guided Diffusion Sampling on Function Spaces (FunDPS) (arxiv.org/abs/2505.17004) - a discretization-agnostic generative framework for solving PDE-based forward and inverse problems. Diffusion-based posterior sampling on function spaces: Our

I'm excited to share our new work, DAPS, an inference-time diffusion sampler for solving general inverse problems without fine-tuning. DAPS significantly improves sample quality across multiple image restoration tasks, particularly in complicated nonlinear inverse problems. DAPS