Yu Cheng
18 papers · 3 citations
Most-cited papers
- UC2: Universal Cross-lingual Cross-modal Vision-and-language Pre-training2021 · 54 citations
- Clip-moe: Towards Building Mixture Of Experts For CLIP With Diversified Multiplet Upcycling2024 · 1 citations
- Large-scale Adversarial Training For Vision-and-language Representation Learning2020
- Dialog-based Interactive Image Retrieval2018
- Training Llms To Be Better Text Embedders Through Bidirectional Reconstruction2025
Top co-authors
Topics