William Peebles
VERIFIED TECHNICAL DOSSIERSources checked

William Peebles

Research Scientist (Sora Lead)

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by William Peebles. Every entry undergoes editorial source verification.

#1
IMPLEMENTATION Checked 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.

Model & Execution Context:Latent Diffusion Model (LDM) latents, ViT architecture, adaLN conditioning.
Scope & Limitations

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

#2
RESEARCH Checked 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.

Model & Execution Context:Graph hypernetworks, weight-space diffusion, permutation invariance.
Scope & Limitations

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