Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM
机构 * Fudan University(复旦大学)
专题命中 多模态训练与对齐 :multimodal(title,abstract);MLLM(title,abstract);分类 cs.CL
Comments Accepted by Findings of EMNLP2025
AI 大模型
跨文本、图像、视频、音频等模态的大模型与学习方法。
机构 * Fudan University(复旦大学)
专题命中 多模态训练与对齐 :multimodal(title,abstract);MLLM(title,abstract);分类 cs.CL
Comments Accepted by Findings of EMNLP2025
机构 * Samueli School of Engineering, Electrical and Computer Engineering, UCLA(UCLA电气与计算机工程学院萨姆利学校)
专题命中 多模态训练与对齐 :cross-modal(title,abstract);multi-modal(abstract);分类 cs.CV
Comments This paper is submitted to IEEE International Conference on Robotics and Automation (ICRA) 2026
机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) ; Li Auto Inc.(Li汽车公司) ; the School of Aeronautics and Astronautics, Xiamen University(厦门大学航空航天学院) ; The Hong Kong University of Science and Technology(香港科技大学)
专题命中 多模态训练与对齐 :multimodal(title,abstract);分类 cs.CV、cs.AI
机构 * VCIP, CS, Nankai University(视觉计算研究所,计算机科学,南开大学)
专题命中 多模态训练与对齐 :multi-modal(title,abstract);分类 cs.CV
Comments Accepted by NeurIPS 2025
机构 * HangZhou Dianzi University(杭州电子大学) ; Shenzhen Polytechnic University(深圳职业技术大学) ; WuHan University(武汉大学)
专题命中 多模态训练与对齐 :multi-modal(abstract);分类 cs.CV
机构 * School of Intelligent Systems Engineering, Sun Yat-Sen University(智能系统工程学院,中山大学)
专题命中 多模态训练与对齐 :multimodal(abstract);分类 cs.CV