Publications

Wei Yu^*, Runjia Qian^*, Yumeng Li^*, Liquan Wang, Songheng Yin, Sri Siddarth Chakaravarthy P, Dennis Anthony, Yang Ye, Yidi Li, Weiwei Wan, Animesh Garg (2026). MosaicMem: Hybrid Spatial Memory for Controllable Video World Models. Preprint.

PDF Project Cite

Gemma Canet Tarres, Manel Baradad, Francesc Moreno-Noguer, Yumeng Li (2026). PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories. In CVPR 2026.

Yumeng Li, William Beluch, Margret Keuper, Dan Zhang, Anna Khoreva (2024). VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis. In ICLR 2025.

PDF Code Project Cite

Jiayi Wang, Kevin A. Laube, Yumeng Li, Jan H. Metzen, Shin-I Cheng, Julio Borges, Anna Khoreva (2024). Label-free Neural Semantic Image Synthesis. In ECCV 2024.

PDF Project Cite

Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva (2024). Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive. In ICLR 2024.

PDF Code Project Cite

Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva (2023). Divide & Bind Your Attention for Improved Generative Semantic Nursing. In BMVC 2023 (Oral).

PDF Code Project Cite

Dan Zhang, Kaspar Sakmann, William Beluch, Robin Hutmacher, Yumeng Li (2023). Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation. In BRAVO Workshop at ICCV 2023.

Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva (2023). Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization. In IJCV.

Yumeng Li, Dan Zhang, Margret Keuper, Anna Khoreva (2023). Intra-Source Style Augmentation for Improved Domain Generalization. In WACV 2023.

Yumeng Li, Ning Gao, Hanna Ziesche, Gerhard Neumann (2022). Category-Agnostic 6D Pose Estimation with Conditional Neural Processes. In WiCV Workshop at CVPR 2022.

PDF Poster Cite