arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Huazhong University of Science and Technology(华中科技大学)

2026-05-15 至 2026-05-15 共收录 5
2605.14923 2026-05-15 cs.CV

SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding

SceneParser: 用于视觉语义理解的分层场景解析

Pengxin Xu, Xincheng Lin, Luping Xiao, Qing Jiang, Meishan Zhang, Hao Fei, Shanghang Zhang, Xingyu Chen

机构 * Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) Zhongguancun Academy(中关村学院) Huazhong University of Science and Technology(华中科技大学) Beijing University of Posts and Telecommunications(北京邮电大学) South China University of Technology(华南理工大学) University of Oxford(牛津大学) Peking University(北京大学)

AI总结 本文提出SceneParser,通过分层解析任务构建场景-对象-部件-功能的层次结构,利用结构完成伪标签和课程学习提升结构感知能力,实验表明其在复杂场景理解中表现更优。

Comments Preprint. Code, models, and dataset are provided in the manuscript

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.14571 2026-05-15 cs.RO cs.LG

Let Robots Feel Your Touch: Visuo-Tactile Cortical Alignment for Embodied Mirror Resonance

让机器人感受你的触摸:用于具身镜像共振的视觉-触觉皮层对齐

Tianfang Zhu, Ning An, Rui Wang, Jiasi Gao, Qingming Luo, Anan Li, Guyue Zhou

机构 * Institute for AI Industry Research, Tsinghua University(清华大学人工智能产业研究院) Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University(海南省生物医学工程重点实验室,海南大学生物医学工程学院) School of New Media Art and Design, Beihang University(北航艺术与设计学院) MoE Key Laboratory for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology(教育部生物医学光子学重点实验室,武汉光电研究所,华中科技大学)

AI总结 本文提出镜像触觉网络,通过多级约束实现视觉与触觉表征的语义、分布和几何对齐,使机器人能从RGB图像预测毫米级触觉信号,为具身镜像共振提供可解释的机器人感知路径。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.07594 2026-05-15 cs.RO

MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents

MemCompiler: 编译,而非注入 -- 用于具身智能体的状态条件化记忆

Xin Ding, Xinrui Wang, Yifan Yang, Hao Wu, Shiqi Jiang, Qianxi Zhang, Liang Mi, Hanxin Zhu, Kun Li, Yunxin Liu, Zhibo Chen, Ting Cao

机构 * University of Science and Technology of China(中国科学技术大学) Huazhong University of Science and Technology(华中科技大学) Microsoft Research(微软研究院) Nanjing University(南京大学) Institute for AI Industry Research (AIR) Tsinghua University(清华大学人工智能产业研究院)

AI总结 MemCompiler通过状态条件化记忆编译提升具身智能体的记忆效率与效果,在多个基准测试中实现性能提升和延迟降低。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.21809 2026-05-15 cs.LG cs.AI q-bio.QM stat.ML

Quotient-Space Diffusion Models

商空间扩散模型

Yixian Xu, Yusong Wang, Shengjie Luo, Kaiyuan Gao, Tianyu He, Di He, Chang Liu

机构 * State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China(一般人工智能国家重点实验室,北京大学,北京,中国) Huazhong University of Science and Technology, Wuhan, China(华中科技大学,武汉,中国) Microsoft Research Asia, Beijing, China(微软亚洲研究院,北京,中国) Zhongguancun Academy, Beijing, China(中关村学院,北京,中国)

AI总结 本文提出商空间扩散模型,通过处理对称性来提升生成模型性能,优于等变模型和对齐方法,在分子结构生成中表现更佳。

Comments ICLR 2026 Oral Presentation; 43 pages, 5 figures, 6 tables; ICLR 2026 Camera Ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05820 2026-05-15 cs.SE cs.AI

From Ranking to Reasoning: Explainable Web API Recommendation via Semantic Reasoning

从排序到推理:通过语义推理实现可解释的Web API推荐

Zishuo Xu, Dezhong Yao, Yao Wan

机构 * School of Software Engineering(软件工程学院) School of Computer Science and Technology(计算机科学与技术学院) Huazhong University of Science and Technology(华中科技大学)

AI总结 本文提出WAR-R1框架,结合语义推理与自适应推荐,通过轻量级大语言模型生成API推荐及自然语言解释,提升推荐准确性和透明度。

详情

展开后加载摘要…

URL PDF HTML 收藏