William Peebles
Research Scientist (Sora Lead)
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
Proof of Work
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.
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 missionLearning 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.
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