自动驾驶

On Offline Evaluation of Vision-based Driving Models

Felipe Codevilla, Antonio M. López, Vladlen Koltun, Alexey Dosovitskiy

专题命中 端到端驾驶 ：autonomous driving(abstract)；分类 cs.CV

Comments Published at the ECCV 2018 conference

End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners

Simon Hecker, Dengxin Dai, Luc Van Gool

专题命中 端到端驾驶 ：self-driving(abstract)；分类 cs.CV

Comments to be published at ECCV 2018

Learning Less is More - 6D Camera Localization via 3D Surface Regression

Eric Brachmann, Carsten Rother

专题命中 端到端驾驶 ：autonomous driving(abstract)；分类 cs.CV

Comments CVPR 2018

Experimental and causal view on information integration in autonomous agents

Philipp Geiger, Katja Hofmann, Bernhard Schölkopf

专题命中 端到端驾驶 ：self-driving(abstract)；分类 cs.AI

Semantic Scene Completion Combining Colour and Depth: preliminary experiments

Andre Bernardes Soares Guedes, Teofilo Emidio de Campos, Adrian Hilton

专题命中 端到端驾驶 ：occupancy(abstract)；分类 cs.CV

Comments 5 pages, 2 figures

Use of Dempster-Shafer Conflict Metric to Detect Interpretation Inconsistency

Jennifer Carlson, Robin R. Murphy

专题命中 端到端驾驶 ：occupancy(abstract)；分类 cs.AI

Comments Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005)

SKGE-SWIN: End-To-End Autonomous Vehicle Waypoint Prediction and Navigation Using Skip Stage Swin Transformer

Fachri Najm Noer Kartiman, Rasim, Yaya Wihardi, Nurul Hasanah, Oskar Natan, Bambang Wahono, Taufik Ibnu Salim

机构 * Department of Computer Science, Indonesia University of Education（印度尼西亚教育大学计算机科学系） ； Research Center for Smart Mechatronics, National Research and Innovation Agency（国家研究与创新局智能机电研究中心） ； Department of Computer Science and Electronics, Gadjah Mada University（加查玛达大学计算机科学与电子系） 纠错

专题命中 端到端驾驶 ：分类 cs.RO、cs.CV、cs.AI；autonomous driving(comments)

Comments keywords-multitask learning, autonomous driving, end-to-end learning, skip connections, swin transformer, self-attention mechanism. 12 pages

Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry

Kashmira Shinde, Jongseok Lee, Matthias Humt, Aydin Sezgin, Rudolph Triebel

专题命中 端到端驾驶 ：分类 cs.RO、cs.CV、eess.IV；autonomous driving(comments)

Comments Published at Workshop on AI for Autonomous Driving (AIAD), the 37th International Conference on Machine Learning, Vienna, Austria, 2020

SLAC: Access-Driven CPU-to-GPU Side-channel Attacks via System-Level Cache on Apple Silicon

SLAC：基于Apple Silicon系统级缓存的访问驱动CPU到GPU侧信道攻击

Tianhong Xu, Saion K. Roy, Ruyi Ding, Aidong Adam Ding, Yunsi Fei

专题命中 端到端驾驶 ：occupancy(abstract)

AI总结 本研究针对Apple Silicon异构SoC发现GPU内存访问会在共享SLC留下可被CPU观测的集合级足迹，提出CPrime+CProbe及加速变体GPrime+CProbe侧信道技术，实现GNN图边重构与LLM隐私攻击，揭示Apple Silicon的微架构漏洞。

Comments Accepted to ACM CCS 2026. 15 pages

TARGET: Automated Scenario Generation from Traffic Rules for Testing Autonomous Vehicles via Validated LLM-Guided Knowledge Extraction

Yao Deng, Jiaohong Yao, Zhi Tu, Xi Zheng, Mengshi Zhang, Tianyi Zhang

专题命中 端到端驾驶 ：autonomous driving(abstract)

Journal ref IEEE Transactions on Software Engineering, Jul. 2025, pp. 1950-1968, vol. 51

MatDiffract: A Material-Informed Automated Analysis Platform for X-ray Powder Diffraction

MatDiffract：用于X射线粉末衍射的材料信息自动分析平台

Hongqing Wang, Mingwei Chen, Hongjie Luo, Wen Yin, Fazhi Qi, Xuqing Chai, Miao Liu, Fengyao Hou

专题命中 端到端驾驶 ：self-driving(abstract)

AI总结 MatDiffract平台致力于解决XRPD数据自动解释问题，基于Atomly数据库，通过构建模拟衍射数据库等方法，实现了对XRPD的高通量表征，在单相和多相混合物测试中取得高准确率，能快速输出完整晶体学结果，支持新材料系统扩展。

Comments 19 pages, 7 figures

A Unified Multi-Modal Sensing and Active-Stabilization Framework for Autonomous IoT Nodes in Connectivity-Denied Environments: From Perimeter Sentinel to High-Value Cargo Protection

用于连接受限环境中自主物联网节点的统一多模态传感与主动稳定框架：从周边哨兵到高价值货物保护

Naahi Mumtaj Rihan

专题命中 端到端驾驶 ：LiDAR(abstract)

AI总结 探讨连接受限环境下自主物联网节点需求，提出广义节点架构，扩展其传感与通信模态，通过复合风险指数耦合遥测与地理信息系统，统一两种部署模式并给出分析与实例。

Above the Inner Loop: Exceeding Accelerate at LLM Prefill GEMM on the M1 AMX

在内循环之上：在M1 AMX上超越Accelerate的LLM预填充GEMM

Deyvik Bhan

专题命中 端到端驾驶 ：occupancy(abstract)

AI总结 通过微基准测试发现M1 AMX的内循环受限于加载-发射，手写内核通过细粒度多线程面板和预打包权重两个部署级杠杆超越Accelerate，在12种LLM预填充GEMM形状上实现1.17倍到2.0倍的加速，且位精确。

Comments 11 pages, 2 figures, 6 tables. Code: https://github.com/dbhan08/inferc

PERTINENCE: Input-based Opportunistic Neural Network Dynamic Execution

PERTINENCE: 基于输入的动态神经网络执行

Omkar Shende, Gayathri Ananthanarayanan, Marcello Traiola

机构 * Department of Computer Science and Engineering, Indian Institute of Technology Dharwad, Karnataka, India（印度理工学院达沃德分校计算机科学与工程系） ； University of Rennes, CNRS, Inria, IRISA, Rennes, France（法国雷恩大学、CNRS、Inria、IRISA） 纠错

专题命中 端到端驾驶 ：occupancy(abstract)

AI总结 提出PERTINENCE运行时方法，通过ML调度器从预训练模型中选择最轻量模型处理每个输入，使用遗传算法优化精度与计算成本的帕累托前沿，在多个视觉任务上减少高达36%计算量且精度不变或提升。

Data-driven invariant set for nonlinear systems with application to command governors

非线性系统的数据驱动不变集及其在指令调节器中的应用

Ali Kashani, Claus Danielson

专题命中 端到端驾驶 ：autonomous driving(abstract)

AI总结 提出直接数据驱动方法合成未建模非线性系统的正不变集，用于设计约束满足的指令调节器，通过半定规划学习平方和类李雅普诺夫函数，并利用Lipschitz性质保证鲁棒性。

Journal ref Automatica, 172, 112010 (2005)

Artificial Intelligence for Food Innovation

人工智能助力食品创新

Bianca Datta, Markus J. Buehler, Yvonne Chow, Kristina Gligoric, Dan Jurafsky, David L. Kaplan, Rodrigo Ledesma-Amaro, Giorgia Del Missier, Lisa Neidhardt, Karim Pichara, Benjamin Sanchez-Lengeling, Miek Schlangen, Skyler R. St. Pierre, Ilias Tagkopoulos, Anna Thomas, Nicholas J. Watson, Ellen Kuhl

专题命中 端到端驾驶 ：self-driving(abstract)

AI总结 本文探讨利用人工智能优化食品创新，重点解决可持续蛋白质的开发问题，提出通过AI驱动的闭环设计提升食品生产效率与可持续性。

Comments 16 pages; 4 figures

Autonomous epitaxial atomic-layer synthesis via real-time computer vision of electron diffraction

通过实时电子衍射计算机视觉实现自主自组装原子层合成

Haotong Liang, Yunlong Sun, Ryan Paxson, Chih-Yu Lee, Alex T. Hall, Zoey Warecki, John Cumings, Hideomi Koinuma, Aaron Gilad Kusne, Mikk Lippmaa, Ichiro Takeuchi

专题命中 端到端驾驶 ：self-driving(abstract)

AI总结 本文通过实时计算机视觉实现电子衍射的多维合成参数空间自主导航，显著减少实验次数，用于制备稳定的非稳态功能氧化物相的单相 epitaxial 薄膜。

Comments 30 pages, 10 figures

Skill-Based Autonomous Agents for Material Creep Database Construction

基于技能的自主代理用于材料蠕变数据库构建

Yue Wu, Tianhao Su, Shunbo Hu, Deng Pan

专题命中 端到端驾驶 ：self-driving(abstract)

AI总结 本文提出基于技能的自主代理框架，用于从科学文献中自动提取高保真的材料蠕变数据，实现物理自洽的数据库构建。

NetWorld: Communication-Based Diffusion World Model for Multi-Agent Reinforcement Learning in Wireless Networks

NetWorld: 基于通信的扩散世界模型用于无线网络中的多智能体强化学习

Kechen Meng, Rongpeng Li, Yansha Deng, Zhifeng Zhao, Honggang Zhang

专题命中 端到端驾驶 ：trajectory planning(abstract)

AI总结 NetWorld通过通信增强的扩散世界模型，实现无线网络中多智能体强化学习的少样本泛化和高效轨迹规划。

Meeting Deadlines in Motion: Deep RL for Real-Time Task Offloading in Vehicular Edge Networks

车辆移动边缘计算中的截止期限问题：深度强化学习在车载边缘网络中的实时任务卸载

Mahsa Paknejad, Parisa Fard Moshiri, Murat Simsek, Burak Kantarci, Hussein T. Mouftah

专题命中 端到端驾驶 ：autonomous driving(abstract)

AI总结 本文提出利用深度强化学习优化车载边缘网络中的实时任务卸载，通过实验验证DQN模型在减少任务执行时间和延迟方面的有效性。

Comments 8 pages, 7 figures, Accepted to IEEE 16th International Conference on Network of the Future (NoF) 2025

DataScribe: An AI-Native, Policy-Aligned Web Platform for Multi-Objective Materials Design and Discovery

DataScribe：面向多目标材料设计与发现的AI原生、政策对齐的Web平台

Divyanshu Singh, Doguhan Sarıtürk, Cameron Lea, Md Shafiqul Islam, Raymundo Arroyave, Vahid Attari

机构 * organization= Department of Computer Science, Texas A\&M University , city= College Station , state= TX , postcode= 77843 , country= USA ； organization= Department of Materials Science ； Engineering, Texas A\&M University , city= College Station , state= TX , postcode= 77843 , country= USA 纠错

专题命中 端到端驾驶 ：self-driving(abstract)

AI总结 DataScribe是一个AI原生、政策对齐的Web平台，通过统一异构数据、整合多目标优化和可解释性，实现材料设计与发现的闭环流程。

Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication

Libra：释放GPU异构性以实现高性能稀疏矩阵乘法

Jinliang Shi, Shigang Li, Youxuan Xu, Xueying Wang, Rongtian Fu, Zhi Ma, Tong Wu

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） 纠错

专题命中 端到端驾驶 ：occupancy(abstract)

AI总结 Libra通过高效利用异构GPU资源，显著提升了稀疏矩阵乘法运算的性能，平均比现有基线方法快1.77至2.9倍。

SenseRay-3D: Generalizable and Physics-Informed Framework for End-to-End Indoor Propagation Modeling

Yu Zheng, Kezhi Wang, Wenji Xi, Gang Yu, Jiming Chen, Jie Zhang

机构 * School of Electrical and Electronic Engineering, The University of Sheffield（电气与电子工程学院，谢菲尔德大学） ； Department of Computer Science, Brunel University London（计算机科学系，布伦尔大学伦敦分校） ； Ranplan Wireless Network Design Ltd.（Ranplan无线网络设计有限公司） ； R&D Department, Cambridge AI+ Ltd.（剑桥AI+有限公司研发部） ； R&D Department, Ranplan Wireless Network Design Ltd.（Ranplan无线网络设计有限公司研发部） 纠错

专题命中 端到端驾驶 ：occupancy(abstract)

Comments Submitted for possible journal publications

Saarthi: An End-to-End Intelligent Platform for Optimising Distributed Serverless Workloads

Siddharth Agarwal, Maria A. Rodriguez, Rajkumar Buyya

专题命中 端到端驾驶 ：self-driving(abstract)

Comments 12 pages, 9 figures, 1 table, 2 algorithms

4D Imaging in ISAC Systems: A Framework Based on 5G NR Downlink Signals

Haoyang Weng, Haisu Wu, Hong Ren, Cunhua Pan, Jiangzhou Wang

专题命中 端到端驾驶 ：autonomous driving(abstract)

Comments TVT

DiSE: A diffusion probabilistic model for automatic structure elucidation of organic compounds

Haochen Chen, Qi Huang, Anan Wu, Wenhao Zhang, Jianliang Ye, Jianming Wu, Kai Tan, Xin Lu, Xin Xu

专题命中 端到端驾驶 ：self-driving(abstract)

L4Span: Spanning Congestion Signaling over NextG Networks for Interactive Applications

Haoran Wan, Kyle Jamieson

专题命中 端到端驾驶 ：occupancy(abstract)

A Reliable and Efficient 5G Vehicular MEC: Guaranteed Task Completion with Minimal Latency

Mahsa Paknejad, Parisa Fard Moshiri, Murat Simsek, Burak Kantarci, Hussein T. Mouftah

专题命中 端到端驾驶 ：autonomous driving(abstract)

Comments 6 pages, 5 Figures, accepted to International Conference on Communications (ICC 2025) Workshops

TEGRA: A Flexible & Scalable NextGen Mobile Core

Bilal Saleem, Omar Basit, Jiayi Meng, Iftekhar Alam, Ajay Thakur, Christian Maciocco, Muhammad Shahbaz, Y. Charlie Hu, Larry Peterson

专题命中 端到端驾驶 ：autonomous driving(abstract)

Comments 12 pages

GPZ: GPU-Accelerated Lossy Compressor for Particle Data

Ruoyu Li, Yafan Huang, Longtao Zhang, Zhuoxun Yang, Sheng Di, Jiajun Huang, Jinyang Liu, Jiannan Tian, Xin Liang, Guanpeng Li, Hanqi Guo, Franck Cappello, Kai Zhao

专题命中 端到端驾驶 ：occupancy(abstract)