Stephan Mandt

Associate Professor@University of California, Irvine·美国·OpenReview

研究方向

Machine Learning for Climate Science · Diffusion Models · Neural Data Compression · Bayesian Deep Learning · Deep Generative Models · Variational Inference · Approximate Bayesian Inference

4.5

UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis

NeurIPS 2025Poster

通讯

6.3

AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data

ICLR 2025Poster

6.2

Heavy-Tailed Diffusion Models

ICLR 2025Poster

5.5

Variational Control for Guidance in Diffusion Models

ICML 2025Poster

通讯

3.5

JANET: Joint Adaptive predictioN-region Estimation for Time-series

合作者 (20)

Stephan Mandt

Parallel Token Prediction for Language Models

Control-Augmented Auto-Regressive Diffusion for Data Assimilation

PIANO: Physics-Informed Autoregressive Networks

Transformers for Mixed-type Event Sequences

Progressive Compression with Universally Quantized Diffusion Models

UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis

AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data

Heavy-Tailed Diffusion Models

Variational Control for Guidance in Diffusion Models

JANET: Joint Adaptive predictioN-region Estimation for Time-series