Wenlin Chen
Scholar

Wenlin Chen

Google Scholar ID: A4zbE2IAAAAJ
University of Cambridge, Max Planck Institute for Intelligent Systems
Machine LearningDeep LearningGenerative ModelsWorld ModelsEmbodied AI
Citations & Impact
All-time
Citations
416
 
H-index
7
 
i10-index
5
 
Publications
15
 
Co-authors
24
list available
Publications
15 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Progressive Tempering Sampler with Diffusion, ICML 2025
  • Training Neural Samplers with Reverse Diffusive KL Divergence, AISTATS 2025
  • Towards Training One-Step Diffusion Models Without Distillation, DeLTa Workshop @ ICLR 2025
  • Your Image is Secretly the Last Frame of a Pseudo Video, DeLTa Workshop @ ICLR 2025
  • Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks, NeurIPS 2024
  • Modelling Variability in Human Annotator Simulation, ACL 2024
  • Diffusive Gibbs Sampling, ICML 2024
  • Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction, ICLR 2023
  • Optimal Client Sampling for Federated Learning, TMLR 2022
  • To Ensemble or Not Ensemble: When Does End-to-End Training Fail?, ECML 2020
Background
  • Research Scientist at Bosch Research (Center for Artificial Intelligence)
  • Based in the Tsinghua-Bosch Joint Research Center on Machine Learning
  • Collaborating with Prof. Jun Zhu’s Research Group at Tsinghua University
  • Interested in core machine learning research and its applications in the physical world
  • Current research focuses on video generation and world modeling using diffusion and autoregressive models for autonomous driving and embodied AI