Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension

Despite significant advancements in vision-language models (VLMs), there lack effective approaches to enhance response quality by scaling inference-time computation. This capability is known to be a core step towards the selfimproving models in recent large language model studies. In this paper, we present Vision Value Model (VisVM) that can guide VLM inference-time search to generate responses with better visual comprehension. Specifically, VisVM not only evaluates the generated sentence quality in the current search step, but also anticipates the quality of subsequent sentences that may result from the current step, thus providing a long-term value. In this way, VisVM steers VLMs away from generating sentences prone to hallucinations or insufficient detail, thereby producing higher quality responses. Experimental results demonstrate that VisVM-guided search significantly enhances VLMs' ability to generate descriptive captions with richer visual details and fewer hallucinations, compared with greedy decoding and search methods with other visual reward signals. Furthermore, we find that self-training the model with the VisVM-guided captions improves VLM's performance across a wide range of multimodal benchmarks, indicating the potential for developing self-improving VLMs.