Generative Modeling via Drifting | MingYang Deng
Portal is the home of the AI for drug discovery community. Join for more details on this talk and to connect with the speakers: https://portal.valencelabs.com/starkl... Paper: Generative Modeling via Drifting https://arxiv.org/abs/2602.04770v1 Abstract: Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and flow-based models. In this paper, we propose a new paradigm called Drifting Models, which evolve the pushforward distribution during training and naturally admit one-step inference. We introduce a drifting field that governs the sample movement and achieves equilibrium when the distributions match. This leads to a training objective that allows the neural network optimizer to evolve the distribution. In experiments, our one-step generator achieves state-of-the-art results on ImageNet at 256 x 256 resolution, with an FID of 1.54 in latent space and 1.61 in pixel space. We hope that our work opens up new opportunities for high-quality one-step generation.
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

MingYang Deng - Generative Modeling via Drifting

Meta Flow Maps enable scalable reward alignment | Peter Potaptchik

Yann LeCun: World Models: Enabling the next AI revolution

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Why birth rates are falling everywhere all at once | FT

AI buys robot and car, does exactly what experts warned.

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

Variational Autoencoders | Generative AI Animated

Zig 2026: No-AI Policy, $670K Foundation, Left GitHub & Why Zig Isn’t 1.0 - Andrew Kelley Explains

Introduction to Generative AI

One-step Language Modeling via Continuous Denoising | Nicholas Boffi

Training Sand to Think: Artificial General Intelligence & Future of Physics

We think this pattern continues forever, but can't prove it

How ASML Makes Chips Faster With Its New $400 Million High NA Machine

Miika Aittala: Elucidating the Design Space of Diffusion-Based Generative Models

Something is jamming GPS over Europe. Here's what we found

I Gave ChatGPT a Body

How SpaceX Humiliated Wall Street
![How AI Learned to Teach Itself [JEPA]](https://i.ytimg.com/vi/gVEr2cnDE_8/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLCVqBgym7bIq_bSKgJFb16dvaV-Cg)
