Tiny-R1V: Lightweight Multimodal Unified Reasoning Model via Model Merging

Qixiang Yin, Huanjin Yao, Jianghao Chen, Jiaxing Huang, Zhicheng Zhao, Fei Su

Keywords: MLLM, Model Merging, Reasoning

Abstract: Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter numerous challenges in terms of reasoning efficiency, such as large model size, overthinking, and compromised accuracy in lightweight scenarios. However, research on the reasoning capabilities of lightweight MLLMs is quite lacking. To this end, we propose Tiny-R1V, a novel lightweight 3B model that achieves faster inference and higher accuracy via a two-stage optimization, while unifying multimodal reasoning across multiple tasks and using fewer tokens. In the first stage, Tiny-R1V introduces Length-Informed Relative Policy Optimization (LIPO), a novel reinforcement learning method, to train each reasoning model. The LIPO is designed to dynamically adjusts advantages of responses within groups, that is, by prioritizing concise yet high-quality responses to encourage the generation of shorter and more accurate response. In the second stage, we propose Adaptive Model Merging (AMM), a training-free model merging method that merges multiple specialist models into a unified architecture. Specifically, AMM adaptively adjusts the weights of task vectors and robustly optimizes the merged vectors via a novel gradient projection regularization loss function, thus mitigating redundant conflicts between them. Extensive evaluations on ten widely-used reasoning benchmarks covering mathematics, structured data (charts, tables, documents), OCR, and general capabilities showcase the superior performance of Tiny-R1V, enabling lightweight models to excel in diverse multimodal reasoning tasks.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 1914