Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using human-preference alignment techniques, such as best-of-n sampling and reinforcement learning. However, these techniques face the difficulty arising from the scarcity of visual preference data, which is required to train a visual reward model (VRM). In this work, we continue the line of research. We present a Robust Visual Reward Model (RoVRM) which improves human-preference alignment for LVLMs. RoVRM leverages auxiliary textual preference data through a three-phase progressive training and optimal transport-based preference data selection to effectively mitigate the scarcity of visual preference data. We experiment with RoVRM on the commonly used vision-language tasks based on the LLaVA-1.5-7B and -13B models. Experimental results demonstrate that RoVRM consistently outperforms traditional VRMs. Furthermore, our three-phase progressive training and preference data selection approaches can yield consistent performance gains over ranking-based alignment techniques, such as direct preference optimization.
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学);National University of Singapore(新加坡国立大学);Zhongguancun Academy(中关村学院)
TextGaze: Prompting Gaze Target Estimation with Textual Scene Cues
University of Science and Technology of China(中国科学技术大学);Hefei University of Technology(合肥工业大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院);Anhui University(安徽大学);United Arab Emirates University(阿联酋大学)
The University of Western Australia(西澳大利亚大学);Murdoch University(莫道克大学);Sun Yat-sen University(中山大学);The Hong Kong University of Science and Technology(香港科技大学)
Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning
Sun Yat-sen University(中山大学);Shenzhen Loop Area Institute(深圳河套学院);Beijing Zhongguancun Academy(北京中关村研究院);Huawei Technologies Co., Ltd(华为技术有限公司);Harbin Institute of Technology(哈尔滨工业大学)
Vision-Language Models are Strong Noisy Label Detectors
School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室);School of Artificial Intelligence, Nanjing University(南京大学人工智能学院)
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
The University of Sydney(悉尼大学);Baidu Inc.(百度公司);Zhejiang University(浙江大学);University of Chinese Academy of Sciences(中国科学院大学);Shanghai AI Laboratory(上海人工智能实验室)
Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China(计算机功率网络与信息安全重点实验室,教育部,山东计算机科学中心(济南国家超级计算机中心),齐鲁大学(山东科学院),济南,中国);Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, China(山东省计算功率互联网与服务计算重点实验室,山东省计算机科学基础研究中心,济南,中国)
Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations
Shanghai Jiao Tong University(上海交通大学);Peking University(北京大学);Beijing University of Chemical Technology(北京化工大学);Nanjing University of Aeronautics and Astronautics(南京航空航天大学);University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学)
GRACE: Boosting Video MLLMs with Grounded Action-Centric Evidence for Viewer Sentiment Prediction
Shanghai Jiao Tong University(上海交通大学);Hangzhou Dianzi University(杭州电子科技大学);The 52nd Research Institute of China Electronics Technology Group Corporation(中国电子科技集团公司第五十二研究所);Hangzhou Bywin Technology Co., Ltd.(杭州百威科技有限公司);Zhejiang Dahua Technology Co., Ltd.(浙江大华技术股份有限公司);School of Information Science and Engineering, Shandong University(山东大学信息科学与工程学院);Haihe Laboratory of Information Technology Application Innovation(海河信息技术应用创新实验室)
StructXLIP: Enhancing Vision-language Models with Multimodal Structural Cues
University of Verona(维罗纳大学);Sapienza University of Rome(罗马大学);University of Trento(特伦托大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);Reykjavik University(雷克雅未克大学)
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
City University of Hong Kong(香港城市大学);University of Science and Technology of China(中国科学技术大学);Utrecht University(乌特勒支大学);University of Electronic Science and Technology of China(电子科技大学)
Enhancing WSI-Based Survival Analysis with Report-Auxiliary Self-Distillation
School of Informatics, Xiamen University, Xiamen, China(厦门大学信息学院);Shanghai Innovation Institution, Shanghai, China(上海创新机构);Nanfang Hospital, Southern Medical University, Guangzhou, China(南方医科大学珠江医院);School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China(中国科学技术大学人工智能与数据科学学院);EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Ales, France(EuroMov数字健康运动);Service de Médecine Nucléaire, Centre Hospitalier Universitaire de Nîmes, Université de Montpellier, Nîmes, France(蒙彼利埃大学尼姆大学医院核医学服务)
Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval
School of Artificial Intelligence(人工智能学院);Beijing University of Posts and Telecommunications(北京邮电大学);Beijing Key Laboratory of Network System and Network Culture(网络系统与网络文化北京市重点实验室)
Language-guided Medical Image Segmentation with Target-informed Multi-level Contrastive Alignments
School of Computer Science, The University of Sydney(悉尼大学计算机科学学院);Institute of Translational Medicine, Shanghai Jiao Tong University(上海交通大学转化医学研究院);Zhongguancun Academy & Zhongguancun Institute of Artificial Intelligence, Beijing, China(北京中关村学院及中关村人工智能研究院);Department of Molecular Imaging, Royal Prince Alfred Hospital(皇家珀斯阿尔弗雷德医院分子成像部)
Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);City University of Hong Kong(香港城市大学);The University of Texas at Arlington(德克萨斯大学阿灵顿分校);School of Biomedical Engineering, ShanghaiTech University(上海科技大学生物医学工程学院);Shanghai United Imaging Intelligence Co., Ltd.(上海联影智能医疗科技有限公司);Shanghai Clinical Research and Trial Center(上海临床研究与试验中心);University of Georgia(佐治亚大学);Massachusetts General Hospital(麻省总医院)
ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking
School of Artificial Intelligence, UCAS(人工智能学院,中国科学院大学);The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA(复杂系统认知与决策智能重点实验室,中国科学院自动化所);School of Physical and Mathematical Sciences, NTU(物理与数学科学学院,国立新加坡大学)
LaCoVL-FER: Landmark-Guided Contrastive Learning Network with Vision-Language Enhancement for Facial Expression Recognition
School of Airspace and Engineering, Shandong University(山东大学航空航天与工程学院);School of Computer Science and Technology, Shandong University of Finance and Economics(山东财经大学计算机科学与技术学院);School of Psychology and Neuroscience, University of Glasgow(格拉斯哥大学心理学与神经科学学院);Faculty of Information Science and Engineering, Ocean University of China(中国海洋大学信息科学与工程学院)