We explore multi-step reasoning in vision-language models (VLMs). The problem is challenging, as reasoning data consisting of multiple steps of visual and language processing are barely available. To overcome the challenge, we first introduce a least-to-most visual reasoning paradigm, which interleaves steps of decomposing a question into sub-questions and invoking external tools for resolving sub-questions. Based on the paradigm, we further propose a novel data synthesis approach that can automatically create questions and multi-step reasoning paths for an image in a bottom-up manner. Our approach divides the complex synthesis task into a few simple sub-tasks, and (almost entirely) relies on open-sourced models to accomplish the sub-tasks. Therefore, the entire synthesis process is reproducible and cost-efficient, and the synthesized data is quality guaranteed. With the approach, we construct $50$k visual reasoning examples. Then, we develop a visual reasoner through supervised fine-tuning, which is capable of generally enhancing the reasoning abilities of a wide range of existing VLMs in a plug-and-play fashion. Extensive experiments indicate that the visual reasoner can consistently and significantly improve four VLMs on four VQA benchmarks. Our code and dataset are available at https://github.com/steven-ccq/VisualReasoner.
MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller
Southern University of Science and Technology(南方科技大学);The Hong Kong University of Science and Technology(香港科技大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Tongji University(同济大学)
Evaluating GPT-5 as a Multimodal Clinical Reasoner: A Landscape Commentary
Department of Radiation Oncology, Winship Cancer Institute, Emory University School of Medicine(放射肿瘤科,Winship癌症研究所,埃默里大学医学院);Department of Biomedical Engineering, Georgia Institute of Technology(生物医学工程系,佐治亚理工学院)
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
School of Electronic and Computer Engineering, Peking University, Shenzhen, China(电子与计算机工程学院,北京大学深圳校区);Tsinghua University, Beijing, China(清华大学,北京);School of Intelligence Science and Technology, Nanjing University, Suzhou, China(智能科学与技术学院,南京大学苏州校区)
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Peng Cheng Laboratory(鹏城实验室);College of Computer Science and Electronic Engineering, Hunan University(湖南大学计算机科学与电子工程学院);University of Chinese Academy of Sciences(中国科学院大学)
DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models
University of Chinese Academy of Sciences(中国科学院大学);Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所信息处理实验室);ByteDance Inc.(字节跳动公司)