Code for NeurIPS 2023 paper "Restart Sampling for Improving Generative Processes"

Code for ICML 2023 paper, "PFGM++: Unlocking the Potential of Physics-Inspired Generative Models"

Code for NeurIPS 2019 Paper, "L_DMI: An Information-theoretic Noise-robust Loss Function"

Code for ICLR 2019 Paper, "MAX-MIG: AN INFORMATION THEORETIC APPROACH FOR JOINT LEARNING FROM CROWDS"

Code for NeurIPS 2022 Paper, "Poisson Flow Generative Models" (PFGM)

Code for ICLR 2021 Paper, "Anytime Sampling for Autoregressive Models via Ordered Autoencoding"

Code for ICLR 2022 Paper, "Controlling Directions Orthogonal to a Classifier"

Code for ICLR 2023 Paper, "Stable Target Field for Reduced Variance Score Estimation in Diffusion Models”

Learning Representations that Support Robust Transfer of Predictors

Code for the ICLR 2020 Paper, "A Theory of Usable Information under Computational Constraints"