← Search

Jiapei Fan

2 accepted papers

2025

Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning

ICML 2025poster

Continual multimodal instruction tuning is crucial for adapting Multimodal Large Language Models (MLLMs) to evolving tasks. However, most existing methods adopt a fixed architecture, struggling with adapting to new tasks due to static model capacity. We propose to evolve the architecture under param…

Cited by 0SourcePDFScholar
2024

NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise

NeurIPS 2024poster

Graph Neural Networks (GNNs) exhibit strong potential in node classification task through a message-passing mechanism. However, their performance often hinges on high-quality node labels, which are challenging to obtain in real-world scenarios due to unreliable sources or adversarial attacks. Conseq…