Han Huang

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining

2024 · arXiv (Cornell University)

Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\textit {de facto}$ …

Prototype Combination for Multi-Source Unsupervised Domain Adaptation

2025 · IEEE Transactions on Emerging Topics in Computational Intelligence

Multi-source unsupervised domain adaptation (MSUDA) is a technique that transfers knowledge from multiple labeled source domains to an unlabeled target domain. The challenge of MSUDA is to reduce the domain shift and effectively amalgamate knowledge …