多模态大模型

Accelerating Multi-modal LLM Gaming Performance via Input Prediction and Mishit Correction

通过输入预测和误位修正加速多模态大语言模型游戏性能

Ziyang Lin, Zixuan Sun, Sanhorn Chen, Xiaoyang Chen, Roy Zhao

专题命中 多模态Agent ：multi-modal(title)；分类 cs.AI

AI总结 通过输入预测和误位修正方法，显著降低多模态大语言模型游戏性能的推理延迟，提升整体控制效果。

Comments UIUC 25 Fall CS 498

Step-GUI Technical Report

Step-GUI 技术报告

Haolong Yan, Jia Wang, Xin Huang, Yeqing Shen, Ziyang Meng, Zhimin Fan, Kaijun Tan, Jin Gao, Lieyu Shi, Mi Yang, Shiliang Yang, Zhirui Wang, Brian Li, Kang An, Chenyang Li, Lei Lei, Mengmeng Duan, Danxun Liang, Guodong Liu, Hang Cheng, Hao Wu, Jie Dong, Junhao Huang, Mei Chen, Renjie Yu, Shunshan Li, Xu Zhou, Yiting Dai, Yineng Deng, Yingdan Liang, Zelin Chen, Wen Sun, Chengxu Yan, Chunqin Xu, Dong Li, Fengqiong Xiao, Guanghao Fan, Guopeng Li, Guozhen Peng, Hongbing Li, Hang Li, Hongming Chen, Jingjing Xie, Jianyong Li, Jingyang Zhang, Jiaju Ren, Jiayu Yuan, Jianpeng Yin, Kai Cao, Liang Zhao, Liguo Tan, Liying Shi, Mengqiang Ren, Min Xu, Manjiao Liu, Mao Luo, Mingxin Wan, Na Wang, Nan Wu, Ning Wang, Peiyao Ma, Qingzhou Zhang, Qiao Wang, Qinlin Zeng, Qiong Gao, Qiongyao Li, Shangwu Zhong, Shuli Gao, Shaofan Liu, Shisi Gao, Shuang Luo, Xingbin Liu, Xiaojia Liu, Xiaojie Hou, Xin Liu, Xuanti Feng, Xuedan Cai, Xuan Wen, Xianwei Zhu, Xin Liang, Xin Liu, Xin Zhou, Yifan Sui, Yingxiu Zhao, Yukang Shi, Yunfang Xu, Yuqing Zeng, Yixun Zhang, Zejia Weng, Zhonghao Yan, Zhiguo Huang, Zhuoyu Wang, Zihan Yan, Zheng Ge, Jing Li, Yibo Zhu, Binxing Jiao, Xiangyu Zhang, Daxin Jiang

机构 * GELab-Team（GELab团队） 纠错

专题命中 多模态Agent ：multimodal(abstract)；分类 cs.CV

AI总结 Step-GUI 是一种先进的 GUI 代理，通过自我进化训练管道和 GUI-MCP 协议，在保持高准确率的同时实现高效隐私保护的 GUI 自动化。

Comments 41 pages, 26 figures

Text-guided multi-stage cross-perception network for medical image segmentation

基于文本引导的多阶段跨感知网络用于医学图像分割

Gaoyu Chen, Haixia Pan

机构 * college of software（软件学院） ； Beihang University（北京航空航天大学） 纠错

专题命中 多模态Agent ：cross-modal(abstract)；分类 cs.CV

AI总结 本文提出文本引导的多阶段跨感知网络TMC，通过多阶段跨注意力模块和多阶段对齐损失提升医学图像分割的跨模态交互和语义一致性，实验表明其在多个数据集上均优于传统方法。