Dr. Jonathan Ho
Independent / ex-OpenAI
Pioneering generative modeling researcher, former research scientist at OpenAI and Google Brain. Lead author of the seminal 2020 paper 'Denoising Diffusion Probabilistic Models' (DDPM) and co-inventor of Classifier-Free Guidance (CFG), establishing the foundational algorithms behind all modern text-to-image and generative video systems.
Areas of focus
Professional niches
Proof of Work
Classifier-Free Diffusion Guidance (CFG)
Invented Classifier-Free Guidance (CFG), a mathematical formulation that jointly trains conditional and unconditional diffusion models, dramatically improving prompt fidelity without requiring separate classifier gradients.
High guidance scales cause over-saturation and high-frequency pixel artifacts without dynamic thresholding.
Context: Conditioning dropout during training, weighted score extrapolation during inference sampling.
View missionDenoising Diffusion Probabilistic Models (DDPM)
First author of the groundbreaking NeurIPS 2020 paper that demonstrated diffusion models could surpass GANs and autoregressive models in generative image fidelity via variational bound simplification.
Standard DDPM required hundreds of sequential sampling steps, requiring modern ODE solvers or flow matching for real-time speed.
Context: Gaussian forward diffusion schedule, reverse Markov chain denoising score matching, U-Net architecture.
View mission