MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
This work addresses the problem of making MLLMs more accessible and scalable for AI developers and users by improving training and inference efficiency, though it appears incremental as it builds on existing MLLM frameworks.
The paper tackles the efficiency bottleneck in Multimodal Large Language Models (MLLMs) by introducing MiniCPM-V 4.5, an 8B parameter model that achieves state-of-the-art performance on benchmarks like OpenCompass and VideoMME, using significantly less GPU memory (46.7%) and inference time (8.7%) compared to larger models.
Multimodal Large Language Models (MLLMs) are undergoing rapid progress and represent the frontier of AI development. However, their training and inference efficiency have emerged as a core bottleneck in making MLLMs more accessible and scalable. To address the challenges, we present MiniCPM-V 4.5, an 8B parameter model designed for high efficiency and strong performance. We introduce three core improvements in model architecture, data strategy and training method: a unified 3D-Resampler model architecture for highly compact encoding over images and videos, a unified learning paradigm for document knowledge and text recognition without heavy data engineering, and a hybrid reinforcement learning strategy for proficiency in both short and long reasoning modes. Comprehensive experimental results in OpenCompass evaluation show that MiniCPM-V 4.5 surpasses widely used proprietary models such as GPT-4o-latest, and significantly larger open-source models such as Qwen2.5-VL 72B. Notably, the strong performance is achieved with remarkable efficiency. For example, on the widely adopted VideoMME benchmark, MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size, using just 46.7\% GPU memory cost and 8.7\% inference time of Qwen2.5-VL 7B.