Yumeng Li

Yumeng Li

PhD Student

Bosch Center for AI

About me

Hi!👋 I’m a third-year PhD student at Bosch Center for Artificial Intelligence (BCAI), supervised by Dr. Anna Khoreva, Dr. Dan Zhang and Prof. Margret Keuper from University of Mannheim. I am passionate about making Generative Models (e.g., GANs, Diffusion Models) greater and their deployment in real-life applications 🤗

Interests
  • Image & Video Synthesis
  • Generative Models
  • Vision-Language Models
  • Out-of-Distribution Generalization
Education
  • PhD in Computer Science, 2022 - Dec. 2024 (Expected)

    University of Mannheim

  • MSc in Simulation Science, 2021

    RWTH Aachen University

  • BSc in Vehicle Engineering, 2019

    Beijing Institute of Technology

Publications

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
Yumeng Li, William Beluch, Margret Keuper, Dan Zhang, Anna Khoreva
Preprint
 Text-to-Video    Temporal Attention    Video Diffusion Model 
VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva
Published at ICLR 2024
 Stable Diffusion    Layout-to-Image    AIGC 
Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
Divide & Bind Your Attention for Improved Generative Semantic Nursing
Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva
Published at BMVC 2023 (Oral)
 Stable Diffusion    Text-to-Image    AIGC 
Divide & Bind Your Attention for Improved Generative Semantic Nursing
Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation
Dan Zhang, Kaspar Sakmann, William Beluch, Robin Hutmacher, Yumeng Li
Published at BRAVO Workshop, ICCV 2023
 Anomaly Detection    Data Augmentation    Autonomous Driving 
Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization
Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva
Published at IJCV
 GAN Inversion    Style Transfer    Domain Generalization     Performance Prediction 
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization
Intra-Source Style Augmentation for Improved Domain Generalization
Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva
Published at WACV 2023
 GAN Inversion    Style Transfer    Domain Generalization 
Intra-Source Style Augmentation for Improved Domain Generalization
Category-Agnostic 6D Pose Estimation with Conditional Neural Processes
Yumeng Li, Ning Gao, Hanna Ziesche, Gerhard Neumann
Presented at WiCV Workshop, CVPR 2022
 6D Pose Estimation    Meta-Learning    Sim2Real 
Category-Agnostic 6D Pose Estimation with Conditional Neural Processes