代码大模型 / AI 编程

Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds

用于非结构化点云各向异性曲面逼近的高维点嵌入学习流形

Hongbo Li, Haikuan Zhu, Xiaohu Guo, Wenping Wang, Jing Hua, Zichun Zhong

专题命中 程序修复 ：repository(abstract)

AI总结 该研究提出HD-PEA框架，通过高维点嵌入等技术实现非结构化点云的各向异性曲面逼近，在多数据集上验证了其泛化性与可用性，性能优于现有方法。

HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents

HDSL：一种用于结构化3D室内场景生成和基于LLM智能体局部编辑的层次化领域特定语言

Letian Li, Chao Shen, Shuzhao Xie, Chenghao Gu, ZhengXiao He, Yu Meng, Xin Yang, Wenyuan Jiang, Zhi Wang

机构 * SIGS, Tsinghua University（清华大学深圳国际研究生院） ； Nankai University（南开大学） ； University of Arizona（亚利桑那大学） ； Zhejiang University（浙江大学） ； ETH Zurich（苏黎世联邦理工学院） 纠错

专题命中 程序修复 ：program repair(abstract)

AI总结 提出HDSL语言，以树结构表示室内场景，结合LLM智能体生成、多模态检索和力导向布局优化，实现结构化场景生成与局部编辑，显著提升对象覆盖率和编辑效率。

Visual-to-Code Authoring, Tensor-Network Debugging, and Quantum-Circuit Inspection Tools in Python

Python中的可视化到代码创作、张量网络调试和量子电路检查工具

Alejandro Mata Ali

专题命中 程序修复 ：code generation(abstract)

AI总结 提出三个互补包：张量网络可视化、张量网络编辑器和量子电路绘制器，分别用于视觉调试、可视化到代码创作和电路检查，以增强张量网络和量子电路的结构可见性和可编辑性。

Comments 15 pages, 6 figures, 6 tables

Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares

Semi-LAR: 基于线性注意力的半监督对比学习用于夜间光斑去除

Xiyu Zhu, Wei Wang, Kui Jiang, Zhengguo Li

机构 * School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China（武汉科技大学计算机科学与技术学院） ； Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China（哈尔滨工业大学计算机学院） ； SRO department, Institute for Infocomm Research, A*STAR, Singapore（新加坡资讯通信研究院SRO部门） 纠错

专题命中 程序修复 ：repository(abstract)

AI总结 本文提出了一种半监督对比学习框架，通过联合处理伪标签可靠性与表征歧视性，有效缓解了夜间光斑去除中的误差累积问题，并通过实验验证了该框架的模型无关性和性能提升。

FireBridge: Cycle-Accurate Hardware + Firmware Co-Verification for Modern Accelerators

FireBridge：面向现代加速器的周期精确硬件+固件联合验证

G Abarajithan, Zhenghua Ma, Francesco Restuccia, Ryan Kastner

专题命中 程序修复 ：repository(abstract)

AI总结 本文提出FireBridge框架，通过将固件与RTL/HLS硬件联合验证，实现加速器系统集成的高效调试，提升调试迭代速度达50倍。

Diversity Over Scale: Whole-Slide Image Variety Enables H&E Foundation Model Training with Fewer Patches

Christoph Bosch, John K. L. Wong, Martin Paulikat, Myroslav Zapukhlyak, Bharti Arora, Manasi Aichmüller-Ratnaparkhe, Jens Baumann, Shivani Karn, Rutuja Kamble, Swapnil Karnik, Bhushan Khedkar, Serey Vathana Chhut, Witali Aswolinskiy, Christian Aichmüller

专题命中 程序修复 ：repository(abstract)

CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction

Jiali Chen, Xusen Hei, HongFei Liu, Yuancheng Wei, Zikun Deng, Jiayuan Xie, Yi Cai, Li Qing

机构 * School of Software Engineering, South China University of Technology（华南理工大学软件学院） ； Key Laboratory of Big Data and Intelligent Robot Ministry of Education（教育部大数据与智能机器人重点实验室） ； The Hong Kong Polytechnic University（香港理工大学） 纠错

专题命中 程序修复 ：program repair(abstract)

Comments ACL 2025 main conference

Novel View Synthesis with Gaussian Splatting: Impact on Photogrammetry Model Accuracy and Resolution

Pranav Chougule

机构 * MS in Robotics \& Autonomous Systems School for Engineering of Matter, Transport \& Energy Arizona State University Tempe, USA 纠错

专题命中 程序修复 ：repository(abstract)

EinHops: Einsum Notation for Expressive Homomorphic Operations on RNS-CKKS Tensors

Karthik Garimella, Austin Ebel, Brandon Reagen

专题命中 程序修复 ：repository(abstract)

Comments 11 pages, 7 figures, 1 table

MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning

Mohammadreza Salehi, Shashanka Venkataramanan, Ioana Simion, Efstratios Gavves, Cees G. M. Snoek, Yuki M Asano

机构 * VIS Lab, UvA（乌得勒支大学视觉实验室） ； Fundamental AI Lab, UTN（UTN基础人工智能实验室） 纠错

专题命中 程序修复 ：repository(abstract)

Comments Accepted to ICCV2025

M$^2$-MFP: A Multi-Scale and Multi-Level Memory Failure Prediction Framework for Reliable Cloud Infrastructure

Hongyi Xie, Min Zhou, Qiao Yu, Jialiang Yu, Zhenli Sheng, Hong Xie, Defu Lian

专题命中 程序修复 ：repository(abstract)

SPIDER: A Comprehensive Multi-Organ Supervised Pathology Dataset and Baseline Models

Dmitry Nechaev, Alexey Pchelnikov, Ekaterina Ivanova

专题命中 程序修复 ：repository(abstract)

Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display

Xinju Wu, Yun Zhang, Chunling Fan, Junhui Hou, Sam Kwong

专题命中 程序修复 ：repository(abstract)

Comments This work has been submitted to the IEEE for possible publication

BACKRUNNER: Mitigating Smart Contract Attacks in the Real World

Chaofan Shou, Yuanyu Ke, Yupeng Yang, Qi Su, Or Dadosh, Assaf Eli, David Benchimol, Doudou Lu, Daniel Tong, Dex Chen, Zoey Tan, Jacob Chia, Koushik Sen, Wenke Lee

专题命中 程序修复 ：program repair(abstract)

Deep Patch Visual SLAM

Lahav Lipson, Zachary Teed, Jia Deng

专题命中 程序修复 ：repository(abstract)

Towards Efficient Controller Synthesis Techniques for Logical LTL Games

Stanly Samuel, Deepak D'Souza, Raghavan Komondoor

专题命中 程序修复 ：program repair(abstract)

TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classification

Litao Yang, Deval Mehta, Sidong Liu, Dwarikanath Mahapatra, Antonio Di Ieva, Zongyuan Ge

专题命中 程序修复 ：repository(abstract)

Comments Accepted for MIDL 2023

FPGA-Patch: Mitigating Remote Side-Channel Attacks on FPGAs using Dynamic Patch Generation

Mahya Morid Ahmadi, Lilas Alrahis, Ozgur Sinanoglu, Muhammad Shafique

专题命中 程序修复 ：program repair(abstract)

Comments 6 pages

Detecting Human-Object Contact in Images

Yixin Chen, Sai Kumar Dwivedi, Michael J. Black, Dimitrios Tzionas

专题命中 程序修复 ：repository(abstract)

Comments Accepted at CVPR 2023

Model Repair via Symmetry

Paul Attie, William Cocke

专题命中 程序修复 ：program repair(abstract)

Comments Full version including proofs

Automated Mammogram Analysis with a Deep Learning Pipeline

Azam Hamidinekoo, Erika Denton, Reyer Zwiggelaar

专题命中 程序修复 ：repository(abstract)

Comments MIDL 2019 [arXiv:1907.08612]

Hey Google, What Exactly Do Your Security Patches Tell Us? A Large-Scale Empirical Study on Android Patched Vulnerabilities

Sadegh Farhang, Mehmet Bahadir Kirdan, Aron Laszka, Jens Grossklags

专题命中 程序修复 ：repository(abstract)

Comments The 2019 Workshop on the Economics of Information Security (WEIS 2019)

Improved Set-based Symbolic Algorithms for Parity Games

Krishnendu Chatterjee, Wolfgang Dvořák, Monika Henzinger, Veronika Loitzenbauer

专题命中 程序修复 ：program repair(abstract)

Comments An extended abstract has been accepted at CSL 2017

Loginson: a transform and load system for very large scale log analysis in large IT infrastructures

Carlos Vega, Paula Roquero, Rafael Leira, Ivan Gonzalez, Javier Aracil

专题命中 程序修复 ：repository(abstract)

Comments 23 pages, Figure 12

Journal ref The Journal of Supercomputing; Volume 73-2017; pp 1-22

A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites

Andrea Lops, Fedelucio Narducci, Azzurra Ragone, Michelantonio Trizio, Claudio Bartolini

机构 * Polytechnic University of Bari \& Wideverse Bari, Italy ； Polytechnic University of Bari Bari, Italy ； Independent Researcher ； University of Bari Bari, Italy 纠错

专题命中 测试生成 ：unit test generation(title,abstract)；code generation(abstract)；分类 cs.SE、cs.AI

Journal ref 2025 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)

Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows

通过受人工测试启发的工作流程进行多智能体大语言模型协作以生成单元测试

Quanjun Zhang, Ye Shang, Siqi Gu, Jianyi Zhou, Chunrong Fang, Zhenyu Chen, Liang Xiao

专题命中 测试生成 ：unit test generation(title,abstract)；repository(abstract)；分类 cs.SE

AI总结 研究针对现有基于大语言模型的单元测试生成方法的局限，提出TestAgent，通过多智能体协作机制模拟人工测试，设计专门智能体、配备工具API并构建知识图谱，在Java项目实验中取得优异结果，性能优于基线和搜索工具。

LLM-based Mockless Unit Test Generation for Java

基于LLM的Java无模拟单元测试生成

Qinghua Xu, Guancheng Wang, Lionel Briand, Zhaoqiang Guo, Kui Liu

专题命中 测试生成 ：unit test generation(title,abstract)；code generation(abstract)；分类 cs.SE

AI总结 提出MocklessTester方法，通过上下文增强生成和约束强制修复解决LLM生成无模拟单元测试时的幻觉问题，在Defects4J和Deps4J上显著提升覆盖率和变异得分。

Enhancing LLM's Ability to Generate More Repository-Aware Unit Tests Through Precise Contextual Information Injection

Xin Yin, Chao Ni, Xinrui Li, Liushan Chen, Guojun Ma, Xiaohu Yang

专题命中 测试生成 ：repository(title,abstract)；unit test generation(abstract)；分类 cs.SE

Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study

大型语言模型参数高效微调用于单元测试生成：一项实证研究

André Storhaug, Jingyue Li

机构 * Norwegian University of Science and Technology（挪威科学技术大学） 纠错

专题命中 测试生成 ：unit test generation(title,abstract)；分类 cs.SE、cs.AI、cs.LG

AI总结 本文通过实证研究探讨了大型语言模型在单元测试生成中的参数高效微调方法，发现LoRA在某些情况下性能可与全量微调媲美，提示微调在成本效益上表现最佳。

Comments 26 pages, 2 figures, 6 tables, 1 listing

LAUDE: LLM-Assisted Unit Test Generation and Debugging of Hardware DEsigns

LAUDE: 基于LLM的硬件设计单元测试生成与调试

Deeksha Nandal, Riccardo Revalor, Soham Dan, Debjit Pal

机构 * Dept. of Electrical and Computer Engineering, University of Illinois Chicago（伊利诺伊大学芝加哥分校电子与计算机工程系） ； Microsoft（微软公司） 纠错

专题命中 测试生成 ：unit test generation(title,abstract)；分类 cs.SE、cs.AI

AI总结 LAUDE利用大语言模型能力，实现硬件设计的单元测试生成与调试，有效检测和修复设计中的错误。

Comments 11 Pages, 9 Figures, 9 Tables Submitted to AAAI 2027