Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results through repeated sampling and selecting the best answer via voting, they play an important role in cross-modal tasks. However, most existing self-consistency methods are limited to a fixed ``repeated sampling and voting'' paradigm and do not reuse historical reasoning information. As a result, models struggle to actively correct visual understanding errors and dynamically adjust their reasoning during iteration. Inspired by the human reasoning behavior of repeated verification and dynamic error correction, we propose the H-GIVR framework. During iterative reasoning, the MLLM observes the image multiple times and uses previously generated answers as references for subsequent steps, enabling dynamic correction of errors and improving answer accuracy. We conduct comprehensive experiments on five datasets and three models. The results show that the H-GIVR framework can significantly improve cross-modal reasoning accuracy while maintaining low computational cost. For instance, using \texttt{Llama3.2-vision:11b} on the ScienceQA dataset, the model requires an average of 2.57 responses per question to achieve an accuracy of 78.90\%, representing a 107\% improvement over the baseline.
Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)计算机科学与技术学院);Pengcheng Laboratory(鹏城实验室);School of Computer Science and Technology, Shandong Jianzhu University(山东建筑大学计算机科学与技术学院)
VLM-Guided Iterative Refinement for Surgical Image Segmentation with Foundation Models
School of Automation Science and Engineering, South China University of Technology, Guangzhou, China(自动化科学与工程学院,华南理工大学,广州,中国);Vanderbilt University, Nashville, TN, USA(范德比尔特大学,纳什维尔,田纳西州,美国);The Pennsylvania State University, University Park, PA , USA(宾夕法尼亚州立大学,大学园,宾夕法尼亚州,美国);Peking University, Beijing , China(北京大学,北京,中国);Virginia Commonwealth University, Richmond, VA, USA(弗吉尼亚共同wealth大学,里士满,弗吉尼亚州,美国);University of California San Diego, San Diego, CA, USA(加州大学圣地亚哥分校,圣地亚哥,加利福尼亚州,美国)
A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
Department of Electrical and Computer Engineering, McGill University(麦吉尔大学电气与计算机工程系);Department of Mechanical, Industrial and Aerospace Engineering, Concordia University(Concordia大学机械、工业与航空航天工程系)
Compiler-Guided Inference-Time Adaptation: Improving GPT-5 Programming Performance in Idris
Ming Hsieh Department of Electrical and Computer Engineering(明希斯部门电子与计算机工程系);Viterbi School of Engineering, University of Southern California(维特比工程学院,南加州大学)
SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
Shanghai Jiao Tong University(上海交通大学);NJIT(新泽西理工学院);Jilin University(吉林大学);Institute of Computing Technology, CAS(中国科学院计算技术研究所);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
The Ohio State University(俄亥俄州立大学);Division of Medicinal Chemistry and Pharmacognosy, The Ohio State University(俄亥俄州立大学药物化学与药物发现部);Department of Biomedical Informatics, The Ohio State University(俄亥俄州立大学生物医学信息学系);Translational Data Analytics Institute, The Ohio State University(俄亥俄州立大学转化数据分析研究所)
SGIC: A Self-Guided Iterative Calibration Framework for RAG
NLP 2 CT Lab, Department of Computer and Information Science, University of Macau(自然语言处理2CT实验室,计算机与信息科学系,澳门大学);Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China(计算与智能学院,哈尔滨工业大学深圳校区,中国)
Topic-Guided Self-Introduction Generation for Social Media Users
The Hong Kong Polytechnic University(香港理工大学);Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)