Stephan Mandt

Dr. Stephan Mandt

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 October 2023 in Entropy
Verified
Journal Article
Open access
PDF file
RYRuihan Yang
Ruihan Yang
PSPrakhar Srivastava
Prakhar Srivastava
SMStephan Mandt
Stephan Mandt
Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end optimized video diffusion model inspired by recent advances in neural video compression. The model successively generates future frames by correcting a deterministic next-frame prediction using a stochastic residual generated by an inverse diffusion process. We compare this approach against six baselines on four datasets involving natural and simulation-based videos. We find significant improvements in terms of perceptual quality and probabilistic frame forecasting ability for all datasets.

25 April 2023 in Foundations and Trends in Computer Graphics and Vision
Verified
Journal Article
Open access
PDF file
YYYibo Yang
Yibo Yang
SMStephan Mandt
Stephan Mandt
LTLucas Theis
Lucas Theis
Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression algorithms to be learned end-to-end from data using powerful generative models such as normalizing flows, variational autoencoders, diffusion probabilistic models, and generative adversarial networks. This monograph aims to introduce this field of research to a broader machine learning audience by reviewing the necessary background in information theory (e.g., entropy coding, rate-distortion theory) and computer vision (e.g., image quality assessment, perceptual metrics), and providing a curated guide through the essential ideas and methods in the literature thus far.

31 October 2024 in Chemical Science
Verified
Journal Article
Open access
PDF file
TSThomas Specht
Thomas Specht
MNMayank Nagda
Mayank Nagda
SFSophie Fellenz
Sophie Fellenz
SMStephan Mandt
Stephan Mandt
HHHans Hasse
Hans Hasse
FJFabian Jirasek
Fabian Jirasek
We introduce HANNA, the first hybrid neural network model that strictly complies with all thermodynamic consistency criteria for predicting activity coefficients and outperforms current benchmark methods in terms of accuracy and applicability.

10 September 2020 in Chemical Communications
Verified
Journal Article
Closed access
PDF file
FJFabian Jirasek
Fabian Jirasek
RBRobert Bamler
Robert Bamler
SMStephan Mandt
Stephan Mandt
We present a generic, highly effective approach to combine physical and data-driven prediction methods for physicochemical properties based on Bayesian machine learning and model distillation.

20 December 2024 in Chemical Engineering Journal
Verified
Journal Article
Open access
NHNicolas Hayer
Nicolas Hayer
TWThorsten Wendel
Thorsten Wendel
SMStephan Mandt
Stephan Mandt
HHHans Hasse
Hans Hasse
FJFabian Jirasek
Fabian Jirasek

22 March 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
RYRuihan Yang
Ruihan Yang
YYYibo Yang
Yibo Yang
JMJoseph Marino
Joseph Marino
SMStephan Mandt
Stephan Mandt
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view recently proposed neural video coding algorithms through the lens of deep autoregressive and latent variable modeling. We present these codecs as instances of a generalized stochastic temporal autoregressive transform, and propose new avenues for further improvements inspired by normalizing flows and structured priors. We propose several architectures that yield state-of-the-art video compression performance on high-resolution video and discuss their tradeoffs and ablations. In particular, we propose (i) improved temporal autoregressive transforms, (ii) improved entropy models with structured and temporal dependencies, and (iii) variable bitrate versions of our algorithms. Since our improvements are compatible with a large class of existing models, we provide further evidence that the generative modeling viewpoint can advance the neural video coding field.