Yu Shen is now a research scientist in Adobe Research, focused on MLLM-based copilot and image compression, e.g., Project Scenic presented in Adobe MAX 2024. His research experiences cover LLM, computer vision, 3D perception, multi-modality learning, robust learning, etc., in real-world applications like MLLM-based copilot, AR/VR/Metaverse, autonomous driving, virtual try-on, etc. Prior to joining Adobe, Yu has worked for Tencent, DJI, and Hiscene. Yu received Computer Science Ph.D. degree in University of Maryland, advised by Prof. Ming Lin.

LinkedIn

Google Scholar

Publications

Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions

Bhattacharya, U., Zhou, Y., Shen, Y., Huang, C., Mitra, S. (Jun. 13, 2025)

Computer Vision and Pattern Recognition Conference (CVPR)

DepthScape: Authoring 2.5D Designs with Depth Estimation

Nguyen, C., Shen, Y., Petrangeli, S., Gadelha, M. (Apr. 26, 2025)

Consolidated Health Informatics (CHI)

Copiloting Creative 3D Scene Modeling and Visualization with Generative Agents

Petrangeli, S., Shen, Y., Wu, G., Gadelha, M., Nguyen, C., Petrangeli, P. (Dec. 14, 2024)

Neural Information Processing Systems (NeurIPS)

GPU-accelerated Lossless Image Compression with Massive Parallelization

Shen, Y., Wu, G., Swaminathan, V., Wang, H., Petrangeli, S., Yu, T. (Dec. 11, 2023)

IEEE International Symposium on Multimedia (ISM)