About me
Research scientist at Tencent AI Lab.
Research fields:
- AI video codec
- Text-to-Image models
- Multimodal Large Language Model
Publications
Ensembling Diffusion Models via Adaptive Feature Aggregation
Cong Wang, Kuan Tian, et al.
Published in ICLR 2025, 2025
V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation
Cong Wang, Kuan Tian, et al.
Published in Arxiv, 2024
Effortless Cross-Platform Video Codec: A Codebook-Based Method
Kuan Tian, Yonghang Guan, Jinxi Xiang, Jun Zhang, et al.
Published in Arxiv, 2023
Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information
Kuan Tian, Yonghang Guan, Jinxi Xiang, Jun Zhang, et al.
Published in ACM MM, 2023
Mimt: Masked image modeling transformer for video compression
Jinxi Xiang, Kuan Tian, Jun Zhang.
Published in ICLR, 2023
Node-aligned graph convolutional network for whole-slide image representation and classification
Yonghang Guan, Jun Zhang, Kuan Tian, et al.
Published in CVPR, 2022
Weakly-supervised nucleus segmentation based on point annotations: A coarse-to-fine self-stimulated learning strategy
Kuan Tian, Jun Zhang, et al.
Published in MICCAI, 2020
Deep active learning for breast cancer segmentation on immunohistochemistry images
Haocheng Shen, Kuan Tian, et al.
Published in MICCAI, 2020