arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Imperial College London(帝国理工学院)

2026-06-24 至 2026-06-24 共收录 5
2606.24759 2026-06-24 cs.CV cs.AI 新提交

UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving

UniDrive: 面向自动驾驶可解释风险理解的统一视觉-语言与定位框架

Xiaowei Gao, Pengxiang Li, Yitai Cheng, Ruihan Xu, James Haworth, Stephen Law, Yun Ye

机构 * organization= Department of Earth Science \& Engineering, Imperial College London , city= London , postcode= SW7 2AZ , country= United Kingdom organization= SpaceTimeLab, Department of Civil, Environmental Geomatic Engineering, University College London , city= London , postcode= WC1E 6BT , country= United Kingdom organization= Department of Computing, The Hong Kong Polytechnic University , city= Hong Kong , country= China organization= Trinity College, University of Oxford , city= Oxford , postcode= OX1 3BH , country= United Kingdom organization= Department of Geography, University College London , city= London , postcode= WC1E 6BT , country= United Kingdom organization= Centre for Global Infrastructure Resilience, The Bartlett School of Sustainable Construction, University College London , city= London , postcode= WC1E 7HB , country= United Kingdom

AI总结 提出UniDrive框架,通过融合时序推理与高分辨率感知分支,联合生成风险描述和边界框定位,在DRAMA-Reasoning基准上超越现有方法,提升小目标定位和可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.24457 2026-06-24 cs.CV 新提交

Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching

Lite Any Stereo V2:更快更强的零样本立体匹配

Junpeng Jing, Ronglai Zuo, Zhelun Shen, Shangchen Zhou, Rolandos Alexandros Potamias, Stefanos Zafeiriou, Krystian Mikolajczyk, Jiankang Deng

机构 * Imperial College London(帝国理工学院)

AI总结 提出Lite Any Stereo V2超快模型系列,通过2D代价聚合框架和三阶段训练策略(合成监督、自蒸馏、真实知识蒸馏)实现高效零样本立体匹配,在保持低延迟的同时达到最先进精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.24367 2026-06-24 cs.SD stat.AP 新提交

Statistical validation and full-sphere extension of a Bayesian model for human static sound localisation

人类静态声源定位贝叶斯模型的统计验证与全空间扩展

Roberto Barumerli, Fabian Brinkmann, Emanuele Zanoni, Anton Hoyer, Lorenzo Picinali, Michele Geronazzo

机构 * Dyson School of Design Engineering, Imperial College London(帝国理工学院戴森设计工程学院) Audio Communication Group, Technische Universität Berlin(柏林工业大学音频通信组) Department of Industrial Systems Technology and Management, University of Padova(帕多瓦大学工业系统技术与管理系)

AI总结 提出贝叶斯声源定位模型的显式似然函数,通过参数恢复和行为数据拟合验证其可靠性,并比较四种HRTF模板插值方法,发现全空间覆盖和高频保真度是关键。

Comments 16 pages, 6 figures, 3 supplementary figures; submitted to Acta Acustica (special issue on Spatial and Binaural Hearing: From Neural Processes to Applications)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.23742 2026-06-24 cs.LG cs.AI cs.AR 新提交

Low-power analogue neural networks with trainable nonlinear connections for continuous control

具有可训练非线性连接的低功耗模拟神经网络用于连续控制

Ian T. Vidamour, Fernando Aguirre, Thomas J. Hayward, Matthew O. A. Ellis, Charles Swindells, Alexander McDonnell, Martin Trefzer, Finley Robins, Luca Manneschi, Susan Stepney, Tony Kenyon, Oliver J. Sutton, Jack C. Gartside, Ivan Y. Tyukin, Adnan Mehonic, Eleni Vasilaki

机构 * School of Computer Science, University of Sheffield(谢菲尔德大学计算机科学学院) Intrinsic Semiconductor Technologies(Intrinsic Semiconductor Technologies公司) School of Chemical, Biological, and Materials Science Engineering, University of Sheffield(谢菲尔德大学化学、生物与材料科学工程学院) School of Physics, Engineering, and Technology, University of York(约克大学物理、工程与技术学院) Department of Computer Science, University of York(约克大学计算机科学系) Department of Electronic & Electrical Engineering, University College London(伦敦大学学院电子与电气工程系) King’s College London(伦敦国王学院) Blackett Laboratory, Imperial College London(帝国理工学院布莱克特实验室)

AI总结 受Kolmogorov-Arnold网络启发,在连接上放置可训练非线性函数,使每个物理连接成为可学习计算单元,通过现场可编程模拟阵列实现带通滤波器,在连续控制等任务上以更少节点和连接达到高效,预计CMOS实现功耗约30微瓦。

Comments Preprint. Further verification of all simulations is ongoing. Any resulting corrections will be incorporated in a revised version

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.23827 2026-06-24 math.OC cs.LG cs.NA math.NA 新提交

Hessian-augmented Supervised Learning for Hamilton-Jacobi-Bellman PDEs

Hessian增强的Hamilton-Jacobi-Bellman偏微分方程监督学习

Matías Gómez-Aedo, Behzad Azmi, Yuyang Huang, Dante Kalise, Karl Kunisch

机构 * Department of Mathematics, Imperial College London, South Kensington Campus(帝国理工学院伦敦数学系,南肯辛顿校区) Department of Mathematics and Statistics, University of Konstanz(康斯坦茨大学数学与统计学系) RICAM and Institute of Mathematics and Scientific Computing, University of Graz(格拉茨大学RICAM与数学与计算科学研究所)

AI总结 提出一种数据驱动方法,利用最优控制问题中值函数的梯度与Hessian信息增强加权最小二乘回归,显著降低样本复杂度并提高近似精度,在高维问题中采用部分Hessian策略控制成本。

详情

展开后加载摘要…

URL PDF HTML 收藏