arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Alibaba(阿里巴巴)

2026-02-26 至 2026-02-26 共收录 5
2602.21952 2026-02-26 cs.CV

MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving

MindDriver: 引入渐进多模态推理用于自动驾驶

Lingjun Zhang, Yujian Yuan, Changjie Wu, Xinyuan Chang, Xin Cai, Shuang Zeng, Linzhe Shi, Sijin Wang, Hang Zhang, Mu Xu

机构 * Amap, Alibaba Group(阿里集团蚂巴公司) The Hong Kong University of Science and Technology(香港科学与技术大学) The Chinese University of Hong Kong(香港中文大学) Xi’an Jiaotong University(西安交通大学)

AI总结 MindDriver通过渐进多模态推理框架提升自动驾驶系统的推理能力,实现语义到物理空间的转化与轨迹规划,展现优异的性能表现。

Comments CVPR2026; Yujian Yuan and Lingjun Zhang contributed equally with random order

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.20218 2026-02-26 cs.CV

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

DenseGRPO:从稀疏到密集奖励用于流匹配模型对齐

Haoyou Deng, Keyu Yan, Chaojie Mao, Xiang Wang, Yu Liu, Changxin Gao, Nong Sang

机构 * Tongyi Lab, Alibaba Group(阿里集团通义实验室)

AI总结 DenseGRPO通过引入密集奖励机制,解决流匹配模型中稀疏奖励导致的反馈与贡献不匹配问题,提升文本到图像生成的人类偏好对齐效果。

Comments Accepted by ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21698 2026-02-26 cs.CV

E-comIQ-ZH: A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of E-commerce Posters with Chain-of-Thought

E-comIQ-ZH: 一种用于评估电子商务海报细粒度的对齐人类数据集和基准

Meiqi Sun, Mingyu Li, Junxiong Zhu

机构 * Taobao & Tmall Group, Alibaba Group(淘宝与天猫集团、阿里巴巴集团)

AI总结 E-comIQ-ZH提出了一种针对中文电子商务海报生成的对齐人类评估框架,通过构建多维评分数据集和专家校准的链式推理模型,实现了细粒度的自动化评估。

Comments 21pages, 19figures, accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19439 2026-02-26 cs.AI cs.LG math.OC

OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents

OptiRepair:基于LLM代理的闭环供应链优化模型诊断与修复

Ruicheng Ao, David Simchi-Levi, Xinshang Wang

机构 * Massachusetts Institute of Technology(麻省理工学院) Alibaba Group(阿里巴巴集团)

AI总结 OptiRepair通过训练LLM代理实现供应链优化模型的闭环诊断与修复,显著提升修复效率和合理性,解决求解器交互和运营合理性两大难题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22548 2026-02-26 cs.CV cs.RO

JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation

JanusVLN: 通过双隐式记忆解耦语义与空间性用于视觉-语言导航

Shuang Zeng, Dekang Qi, Xinyuan Chang, Feng Xiong, Shichao Xie, Xiaolong Wu, Shiyi Liang, Mu Xu, Xing Wei, Ning Guo

机构 * Xi’an Jiaotong University(西安交通大学) Amap, Alibaba Group(阿里巴巴集团)

AI总结 JanusVLN通过双隐式记忆解耦语义与空间性,提升视觉-语言导航的性能和效率。

Comments Accepted to ICLR 2026. Project page: https://miv-xjtu.github.io/JanusVLN.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏