影响力指数

68.85/100

前 2.9%

全站排名 #1,836

发表论文13 篇

平均评分5.7

年均产出4.3 篇/年

Julius Berner

Researcher@NVIDIA·美国·OpenReview

研究方向

neural operators · generative modeling · sampling · approximation theory · deep learning · statistical learning theory · machine learning · partial differential equations · applied mathematics · numerical analysis

5.0

There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-Training

ICLR 2026Poster

三作

4.0

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

NeurIPS 2025Spotlight

二作

6.8

Underdamped Diffusion Bridges with Applications to Sampling

ICLR 2025Poster

二作

6.8

Robust Representation Consistency Model via Contrastive Denoising

ICLR 2025Poster

二作

6.5

Sequential Controlled Langevin Diffusions

ICLR 2025Poster

三作

6.4

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

NeurIPS 2025Poster

三作

5.3

From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training

ICLR 2025Rejected

一作

5.2

Reduced-Order Neural Operators: Learning Lagrangian Dynamics on Highly Sparse Graphs

合作者 (20)

Julius Berner

There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-Training

Tensor Train Diffusion: A Fast Solver for High-Dimensional Sampling

OPERATOR LEARNING USING WEAK SUPERVISION FROM WALK-ON-SPHERES

Flow-Guided Neural Operator For Self- Supervised Learning On Time Series Data

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

Underdamped Diffusion Bridges with Applications to Sampling

Robust Representation Consistency Model via Contrastive Denoising

Sequential Controlled Langevin Diffusions

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training

Reduced-Order Neural Operators: Learning Lagrangian Dynamics on Highly Sparse Graphs