MiniCPM-V-4_5

Papers using or citing this model 2

• LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images 237 citations · 2024 · arXiv (Cornell University) · arXiv

  Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited...

• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe 192 citations · 2025 · arXiv (Cornell University) · arXiv

  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...