Yang, Guoxing

Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts

2024 · arXiv (Cornell University)

As the research of Multimodal Large Language Models (MLLMs) becomes popular, an advancing MLLM model is typically required to handle various textual and visual tasks (e.g., VQA, Detection, OCR, and ChartQA) simultaneously for real-world applications. …