- Nature Communications’25: MetaQ: Fast, scalable, and accurate metacell inference via single-cell quantization
- AAAI’25: Incomplete Multi-view Clustering via Diffusion Contrastive Generation
- ICLR’24: Multi-granularity Correspondence Learning from Long-term Noisy Videos
- ICCV’23: Graph Matching with Bi-level Noisy Correspondence
- TPAMI’22: Dual Contrastive Prediction for Incomplete Multi-view Representation Learning
- CVPR’21: COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction
Research Experience
Research Experience:
- Multiple projects in the field of multi-modal learning, including robust multi-modal learning, interactive multi-modal learning, and medical AI.
Education
Ph.D. student in the College of Computer Science at Sichuan University, advised by Prof. Xi Peng.
Background
Research Interests: Multi-modal Learning and its applications in AI4Science. Key contributions include:
- Robust Multi-modal Learning: Tackling challenges such as modality missing (CVPR’21, TPAMI’22, AAAI’24-25) and noisy correspondence (ICCV’23, ICLR’24, NeurIPS’24) in image/video-text and image-image data.
- Interactive Multi-modal Learning: Focusing on interactions between users, tools, and external knowledge (ICML’25, LLaVA-ReID, Visual Abstraction).
- Medical AI and Bioinformatics: Focusing on single-cell and multi-omics analysis, addressing key challenges such as representative cell selection (Nature Communications’25) and batch effect correction (TNNLS’23).