William Peebles
Research Scientist (Sora Lead)
Verified Proof of Work Artifacts
2 items catalogedEach 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.
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.
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.
Permutation symmetry in high-dimensional weight spaces makes scaling to multi-billion parameter checkpoints difficult.