Thanks to the ICLR Award Committee! And thank you for the kind words, Max! You were the perfect Ph.D. advisor and collaborator, kind and inspiring. I really couldn't have wished for better.

Diffusion does not have to use continuous state-spaces! Jacob Austin Daniel Johnson Rianne van den Berg Yi Tay We highlight the case for discrete state-space diffusion.

Why should we wait for inference? Jiaming Song Chenlin Meng Stefano Ermon Danilo J. Rezende Robin Rombach Denoising Diffusion Implicit Models (DDIM) improves upon DDPM diffusion models by reducing the time for data generation.

Are you also using LLMs and Reinforcement Learning Human Feedback (RLHF)? John Schulman Prafulla Dhariwal Alec Radford Sergey Levine We better understand why the Proximal Policy Optimization (PPO) algorithm is an important component of RL

Discover the hidden link: Why posterior collapse thrives in VAEs however not in diffusion models. Dr. Ganapathi Pulipaka 🇺🇸 Sebastian Raschka Awni Hannun fly51fly Dive into our latest insights

Are you a creative hiding in plain sight? If your imagination runs wild, then diffusion models might be for you! Bahjat Kawar Jiaming Song Tim Salimans Mohammad Norouzi We discuss DDRM and how it is applied to challenges in denoising, in-painting, de-blurring, super-resolution.

Who needs patience when you’ve got optimization?! Cheng Lu Yuhao Zhou Jun-Yan Zhu Sanja Fidler The method of DPM-Solver is discussed, allowing high-quality data point generation in as little as 10 steps!

Curious about how diffusion models are influenced? Jaakko Lehtinen Alex Nichol Prafulla Dhariwal Tim Salimans Jonathan Ho Check out the review of the Autoguidance #NeurIPS2024 runner-up best paper in the following PDF drive.google.com/file/d/1WxQ7Zd…

Vector-quantization is taking over! ByteDance Keyu Tian Patrick Esser Robin Rombach Oriol Vinyals koray kavukcuoglu The details of VQ methods are highlighted, including the VAR NeurIPS Conference paper of the year. check out the following PDF drive.google.com/file/d/1XnxS0b…

interested in mechanistic interpretability of transformers? Chris Olah Neel Nanda Catherine Olsson a brief look is offered

A history of equations Machine Learning Street Talk Tim Scarfe thank you MLST for hosting a session on all things generative AI. check out the 20 page pdf! drive.google.com/file/d/1Y0ggub…

Chieh-Hsin (Jesse) Lai Yang Song Dongjun Kim Yuki Mitsufuji Stefano Ermon Chieh-Hsin (Jesse) Lai what a great body of work, The Variational Book thevariationalbook.com will be out soon, featuring 140+ intuitive illustrations covering all these seminal topics!

A quick look Danilo J. Rezende Shakir Mohamed Marcus Brubaker at the fundamentals of normalizing flows

The blueprint behind normalizing flows Felix Draxler Mathurin Massias is outlined!

Back to basics Alec Helbling akihiro suzuki back to the flow

Normalizing flows just got better Laurent Dinh Jascha Sohl-Dickstein Jiatao Gu here’s how, an improvement over linear transforms is discussed

Did you ask for more flow layers!? The continuous normalizing flow Ricky T. Q. Chen Peter Holderrieth Neta Shaul is introduced

If you don't know Ilya Sutskever Michael Albergo Robin Rombach Now you know! The Continuous Normalizing Flow model is introduced