Wenbin He
Scholar

Wenbin He

Google Scholar ID: BQG5angAAAAJ
Senior Research Manager and Lead Scientist at Bosch
Machine LearningComputer VisionData VisualizationComputer Graphics
Citations & Impact
All-time
Citations
564
 
H-index
12
 
i10-index
16
 
Publications
20
 
Co-authors
18
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Paper 'InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations' won IEEE VIS 2019 Best Paper Award
  • Paper on parallel reduction received IEEE LDAV 2018 Best Paper Honorable Mention Award
  • Multiple papers published in top-tier venues including IEEE TVCG and IEEE PacificVis
  • Paper on visual analytics for deep reinforcement learning models accepted by PacificVis 2020
  • Paper on kernel density estimation of surfaces accepted by IEEE TVCG in 2018
Research Experience
  • Research Scientist at Bosch, Mar 2020 – Present, working on Human Machine Interaction and Visual Computing
  • Graduate Research Associate at The Ohio State University, May 2013 – Dec 2016 and May 2017 – Dec 2019, worked on exploration and analysis of ensemble datasets using statistical and deep learning models
  • Graduate Teaching Associate at The Ohio State University, Jan 2017 – May 2017, taught CSE 5542 Real-Time Rendering and CSE 5544 Introduction to Data Visualization
  • Summer Intern at Mitsubishi Electric Research Laboratories (MERL), May 2019 – July 2019, developed visual analytics techniques to interpret and diagnose deep reinforcement learning models for robot control, focusing on simulation-to-reality transfer failures
  • Research Aide at Argonne National Laboratory, May 2016 – Aug 2016, developed parallel reduction techniques for visualizing and analyzing extreme-scale datasets on supercomputers
  • Research Aide at Argonne National Laboratory, May 2015 – July 2015, analyzed and visualized finite-time Lyapunov exponents and Lagrangian coherent structures in uncertain unsteady flows using statistical models