Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise (with Zhenkai Zhang and Krista Ehinger)

This paper shows how to improve denoising diffusion models by having the network predict the image and the noise jointly, rather than predicting just one and recovering the other algebraically. The dual prediction provides a richer training signal and a more stable sampling trajectory, Reformulating the noise schedule in terms of the arc on the unit circle between pure-image and pure-noise states removes singularities and enables the use of higher order ODE solvers such as RK4.

[ACML 2023 paper]

Improved Training of Generative Adversarial Networks Using Decision Forests (with Yan Zuo and Gil Avraham)

This paper shows how to use decision forests as the discriminator in a Generative Adversarial Network. The forest's piecewise structure provides a stronger, more stable gradient signal to the generator than a standard CNN discriminator, improving sample diversity and training stability across CIFAR-10, STL-10 and CelebA without any change to the generator architecture.

[WACV 2021 paper]

Parallel optimal transport gan (with Gil Avraham and Yan Zuo)

This paper shows how to address the diversity problem in Generative Adversarial Networks by introducing a loss that explicitly pulls the generated distribution towards the real distribution in a low dimensional latent space.

[CVPR 2019 paper]