CLGRPO: Reasoning Ability Enhancement for Small VLMs

TL;DR

This paper introduces a novel post-training optimization method called CLGRPO to significantly enhance the reasoning abilities of small vision-language models, making them comparable to larger models.

Contribution

The paper presents a four-stage incremental training strategy and a self-supervised COT data construction system to improve reasoning in small VLMs, a novel approach in the field.

Findings

Significant accuracy improvement on EMOSet-118K dataset

Achieved performance comparable to 8B models with 1B SVLM

Enhanced reasoning ability through staged training and CLGRPO

Abstract

Small Vision Language Models (SVLMs) generally refer to models with parameter sizes less than or equal to 2B. Their low cost and power consumption characteristics confer high commercial value. However, their reasoning abilities are limited by the number of parameters. To address this issue, this paper proposes a post-training optimization paradigm called the Incremental Training Strategy to enhance the reasoning ability of SVLMs. Firstly, we constructed a Self-Supervised Chain-of-Thought (COT) Data Construction System, which leverages multiple LVLMs with 7B parameters or more to transform original data into COT data in a self-supervised manner. Our proposed Incremental Training Strategy consists of four stages. Stage 1 injects domain knowledge by performing Supervised Fine-Tuning (SFT) to the pretrained model on the COT data. Stage 2 aligns the COT data format by conducting a small amount of Group Relative Policy Optimization (GRPO) training constrained only by format rewards on the COT data. Stage 3 enhances reasoning ability by applying GRPO training on the COT data with constraints on both format and accuracy rewards. The resulting model shows significant improvement compared to the baseline. Stage 4 addresses the limited capacity of the SVLMs and the weak ability to capture complex patterns by proposing ClipLow GRPO (CLGRPO) to constrain the capture space of the training process. We conducted extensive comparative and ablation experiments on the abstract semantic recognition dataset EMOSet-118K. Experimental results demonstrate that our method significantly improves the reasoning ability of 1B SVLM. Compared to the baseline model fine-tuned on the original data, accuracy increased by 2.77 and recall by 0.69, achieving performance comparable to that of 8B models.