William Peebles

Research Scientist (Sora Lead)

Sources checked
ABOUT

Research Scientist at OpenAI and co-lead of the Sora text-to-video foundation model project, and former PhD researcher at UC Berkeley BAIR. Co-inventor of Diffusion Transformers (DiT), establishing the core architecture for scaling visual generation.

Areas of focus

Professional niches

THE WORK BEHIND THE PROFILE

Proof of Work

implementationChecked Sep 22, 2026

Diffusion Transformers (DiT): The Architectural Backbone of Sora

Engineered and released the open-source DiT PyTorch framework, proving that Transformer scaling laws reliably predict image and video generation fidelity across FLOPs and parameter scales.

Scope & limitations

High sample step requirements (e.g. 50-100 DDIM steps) necessitate distillation techniques for real-time interactive generation.

Context: Latent Diffusion Model (LDM) latents, ViT architecture, adaLN conditioning.

View mission
researchChecked Sep 22, 2026

Learning to Learn with Generative Models of Neural Network Checkpoints

Authored the NeurIPS 2022 paper exploring generative modeling of neural network parameter checkpoints, demonstrating that diffusion models can synthesize functioning weights of performant downstream classifiers.

Scope & limitations

Permutation symmetry in high-dimensional weight spaces makes scaling to multi-billion parameter checkpoints difficult.

Context: Graph hypernetworks, weight-space diffusion, permutation invariance.

View mission

Guides to evaluating AI expertise