Oceania I - MSR 2026

VenueWindsor Convention Center and Hotels

Room nameOceania I

Floor0

Room InformationNo extra information available

Program

This program is tentative and subject to change.

Time Zone

The program is currently displayed in (GMT-03:00) Brasilia, Distrito Federal, Brazil.

Use conference time zone: (GMT-03:00) Brasilia, Distrito Federal, BrazilSelect other time zone

The GMT offsets shown reflect the offsets at the moment of the conference.

Time Band

By setting a time band, the program will dim events that are outside this time window. This is useful for (virtual) conferences with a continuous program (with repeated sessions).
The time band will also limit the events that are included in the personal iCalendar subscription service.

Display full programSpecify a time band

Save

You're viewing the program in a time zone which is different from your device's time zone change time zone

Sun 12 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

09:00 - 10:30	Opening + Keynote (Prof. Zhi Jin)FORGE Program / FORGE Keynotes at Oceania I Chair(s): Gabriele Bavota Software Institute @ Università della Svizzera Italiana, Xing Hu Zhejiang University, Christoph Treude Singapore Management University

09:00 15m Day opening		Opening Message from the Chairs FORGE Keynotes
09:15 75m Keynote		Keynote: How to Enable Large Language Models to Accelerate the Process of Requirements Understanding and Analysis FORGE Keynotes Zhi Jin Peking University, Wuhan University

11:00 - 12:30	Session I - Testing, Quality, and RefactoringFORGE Research Papers / FORGE Data and Benchmarking at Oceania I Chair(s): Rosalia Tufano Università della Svizzera Italiana

11:00 12m Talk		Backporting in Robot Operating System: Identifying Commit Purpose and Propagation Need with Large Language Models FORGE Research Papers Pankaj Manoharlal Thakur North Carolina State University, Kyle Thomson North Carolina State University, Wesley K.G. Assunção North Carolina State University, Bowen Xu North Carolina State University
11:12 6m Talk		PatchGPT: Multi-Agent Patch Backporting without Model Fine-Tuning FORGE Research Papers Ye Liu Singapore Management University, Ruidong Han Singapore Management University, Chengyan Ma Singapore Management University, Yuqing Niu , David Lo Singapore Management University, Ye Liu Nanyang Technological University
11:18 12m Talk		From Human to Machine Refactoring: Assessing GPT-4’s Impact on Python Class Quality and Readability FORGE Research Papers Alessandro Midolo University of Catania, Emiliano Tramontana University of Catania, Massimiliano Di Penta University of Sannio, Italy Pre-print
11:30 12m Talk		XMENTOR: A Rank-Aware Aggregation Approach for Human-Centered Explainable AI in Just-in-Time Software Defect Prediction FORGE Research Papers Saumendu Roy University of Saskatchewan, Banani Roy University of Saskatchewan, Chanchal K. Roy University of Saskatchewan, Richard Bassey University of Saskatchewan
11:42 12m Talk		Exploring the Potential of Large Language Models in Simulink-Stateflow Mutant Generation FORGE Research Papers Pablo Valle Mondragon University, Shaukat Ali Simula Research Laboratory and Oslo Metropolitan University, Aitor Arrieta Mondragon University Pre-print
11:54 6m Talk		Tricky²: Towards a Benchmark for Evaluating Human and LLM Error Interactions FORGE Data and Benchmarking Cole Granger William & Mary, Dipin Khati William & Mary, Daniel Rodriguez-Cardenas William & Mary, Denys Poshyvanyk William & Mary
12:00 12m Talk		Reasoning about Multi-hop Fault Propagation with LLM Agents for Root Cause Analysis in Cloud-based Systems FORGE Research Papers Evelien Riddell University of Waterloo, James Riddell University of Waterloo, Gengyi Sun University of Waterloo, Michal Antkiewicz University of Waterloo, Canada, Krzysztof Czarnecki University of Waterloo, Canada, Evelien Riddell University of Waterloo Pre-print
12:12 12m Talk		Execution-free Agentic Program Repair for Enterprise-Scale Development FORGE Research Papers Saurabh Bodhe Advanced Micro Devices (AMD), Sanjukta De Advanced Micro Devices, Subhayan Roy Advanced Micro Devices (AMD), Jaydip Pokiya Advanced Micro Devices (AMD), Indira Vats University of Toronto; Advanced Micro Devices (AMD), Sehajpreet Kaur Advanced Micro Devices (AMD), Monica Li Advanced Micro Devices (AMD), Lejin Varghese Advanced Micro Devices (AMD), Max Kiehn Advanced Micro Devices (AMD), Yonas Bedasso Advanced Micro Devices

14:00 - 15:30	Session II - Human-AI Collaboration, Multi-agent Systems, & BenchmarkingFORGE Data and Benchmarking / FORGE Research Papers at Oceania I Chair(s): Massimiliano Di Penta University of Sannio, Italy

14:00 12m Talk		Reporting LLM Prompting in Automated Software Engineering: A Guideline Based on Current Practices and Expectations FORGE Research Papers Alexander Korn University of Duisburg-Essen, Lea Zaruchas University of Cologne, Chetan Arora Monash University, Andreas Metzger paluno – The Ruhr Institute for Software Technology, University of Duisburg-Essen, Sven Smolka University of Duisburg-Essen, Fanyu Wang Monash University, Andreas Vogelsang paluno – The Ruhr Institute for Software Technology, University of Duisburg-Essen, Alexander Korn University of Duisburg-Essen
14:12 12m Talk		Impacts of Generative AI on Agile Teams' Productivity: A Multi-Case Longitudinal Study FORGE Research Papers Rafael Tomaz Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Paloma Guenes Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Allysson Allex Araújo Federal University of Cariri, Maria Teresa Baldassarre Department of Computer Science, University of Bari , Marcos Kalinowski Pontifical Catholic University of Rio de Janeiro (PUC-Rio) Pre-print
14:24 6m Talk		Visual Loop: Bridging the Cognitive Gap in Software Development Through Visual-AI Collaboration FORGE Research Papers Luis F. Gomes Carnegie Mellon University, Xin Zhou Singapore Management University, Singapore, David Lo Singapore Management University, Rui Abreu Faculty of Engineering of the University of Porto, Portugal, Rui Abreu University of Porto
14:30 12m Talk		AutoReSpec: A Framework for Generating Specification using Large Language Models FORGE Research Papers Ragib Shahariar Ayon Texas State University, Shibbir Ahmed Texas State University Pre-print Media Attached
14:42 6m Talk		CodeViz: Collaborative Multi-Agent System for Analytical and Visualization Tasks in Data Science FORGE Research Papers Sai Sanjna Chintakunta Pennsylvania State University, Nathalia Nascimento Pennsylvania State University, Everton Guimaraes Pennsylvania State University
14:48 6m Talk		SEMODS: A Validated Dataset of Open-Source Software Engineering Models FORGE Data and Benchmarking Alexandra González Universitat Politècnica de Barcelona - BarcelonaTech (UPC), Xavier Franch Universitat Politècnica de Catalunya, Silverio Martínez-Fernández UPC-BarcelonaTech DOI Pre-print
14:54 6m Talk		Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering FORGE Data and Benchmarking Daniel Rodriguez-Cardenas William & Mary, Xiaochang Li William & Mary, Marcos Macedo Queen's University, Antonio Mastropaolo William and Mary, USA, Dipin Khati William & Mary, Yuan Tian Queen's University, Kingston, Ontario, Huajie Shao College of William & Mary, Denys Poshyvanyk William & Mary
15:00 6m Talk		OmniBench-RAG: A Multi-Domain Evaluation Platform for Retrieval-Augmented Generation Tools FORGE Data and Benchmarking Jiaxuan Liang Huazhong University of Science and Technology, China, shide zhou Huazhong University of Science and Technology, Kailong Wang Huazhong University of Science and Technology, JIAXUAN LIANG Huazhong University of Science and Technology

16:00 - 17:30	Industry Keynotes IFORGE Keynotes at Oceania I Chair(s): Chao Peng ByteDance

16:00 45m Keynote		Semantics Matters: Architecting Business Context for Generative AI in Software Engineering FORGE Keynotes Nicole Davila Zup Innovation & UFRGS
16:45 45m Keynote		The Mindful IDE: From Noise to Nuance FORGE Keynotes Maliheh Izadi Delft University of Technology

Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

09:00 - 10:30	Keynote (Prof. Michael Pradel) + AwardsFORGE Program / FORGE Keynotes at Oceania I Chair(s): Gabriele Bavota Software Institute @ Università della Svizzera Italiana

09:00 75m Keynote		Keynote: Natural Language as Specification: LLM-Based Validation of Software Evolution FORGE Keynotes Michael Pradel CISPA Helmholtz Center for Information Security
10:15 15m Awards		Awards session FORGE Keynotes

11:00 - 12:30	Session III - Code Generation & MigrationFORGE Data and Benchmarking / FORGE Research Papers at Oceania I Chair(s): Daniel Rodriguez-Cardenas William & Mary

11:00 6m Talk		Deep Graph-Language Fusion for Structure-Aware Code Generation FORGE Research Papers Mert Tiftikci TU Darmstadt; hessian.AI, Amir Molzam Sharifloo TU Darmstadt, Mira Mezini TU Darmstadt; hessian.AI; National Research Center for Applied Cybersecurity ATHENE, Mert Tiftikci Technical University of Darmstadt
11:06 12m Talk		Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation FORGE Research Papers Laboni Sarker University of California at Santa Barbara, Mara Downing , Achintya Desai University of California, Santa Barbara, Tevfik Bultan University of California at Santa Barbara
11:18 6m Talk		Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis FORGE Research Papers Dipin Khati William & Mary, Daniel Rodriguez-Cardenas William & Mary, Paul Pantzer William & Mary, Denys Poshyvanyk William & Mary
11:24 12m Talk		Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Code Health Metrics FORGE Research Papers Markus Borg CodeScene, Nadim Hagatulah Lund University, Adam Tornhill Codescene AB, Emma Söderberg Lund University Pre-print
11:36 6m Talk		VHDL-Instruct: Training Open Dataset for LLMs Benchmarking and HDL Code Generation FORGE Data and Benchmarking Patrik Drazic University of Southern Denmark, Benaoumeur Senouci University of Southern Denmark, Boualem Benatallah Dublin City University
11:48 6m Talk		COMPASS: A Psychometrics-Guided Multi-Dimensional Benchmark for Code Generation Evaluation FORGE Data and Benchmarking James Meaden Codility, Markus Borg CodeScene Pre-print
11:54 6m Talk		A Hybrid LLM-Guided Approach to Code Migration Using API-Derived Rules FORGE Research Papers Gabriel Vitor Klaumann Gubert Technische Hochschule Ingolstadt (THI), Stefan Kugele Technische Hochschule Ingolstadt, Munir Georges Technische Hochschule Ingolstadt (THI)
12:00 12m Talk		An Experience Report on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights FORGE Research Papers Zhili Zeng York University, Kimya Khakzad Shahandashti York University, Alvine Boaye Belle York University, Song Wang York University, Zhen Ming (Jack) Jiang York University
12:12 6m Talk		MiG.4: A Curated Dataset of Library Migrations in Java and Python FORGE Data and Benchmarking Matheus Barbosa UFMG, Pedro Baptista UFMG, João Eduardo Montandon Universidade Federal de Minas Gerais (UFMG), MATHEUS LIMA Ufmg, Pedro Henrique Fernandes Baptista UFMG
12:18 6m Talk		PromiseAwait: A Dataset of JavaScript Migrations from Promises to Async/Await FORGE Data and Benchmarking Rafael Araujo Magesty UFMG, João Eduardo Montandon Universidade Federal de Minas Gerais (UFMG), Rafael Magesty

14:00 - 15:30	Industry Keynotes IIFORGE Program / FORGE Keynotes at Oceania I Chair(s): Christoph Treude Singapore Management University

14:00 45m Keynote		Lingxi - Towards Domain Knowledge Guided Repo-level Code Generation Practice in Huawei FORGE Keynotes Kui Liu Huawei
14:45 45m Keynote		Same Brain, Superpowers: Programming in the Age of AI FORGE Keynotes Chris Parnin Microsoft

16:00 - 17:00	Session IV - Security & PrivacyFORGE Research Papers / FORGE Data and Benchmarking at Oceania I Chair(s): Zhou Yang University of Alberta, Alberta Machine Intelligence Institute

16:00 12m Talk		PIChecker: Automatic Privacy Detector for Third Party Libraries in Android Apps FORGE Research Papers Kerui Huang , Xian Zhan Southern University of Science and Technology, Xin Xia Zhejiang University
16:12 12m Talk		DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells FORGE Research Papers Houcine Abdelkader Cherief Ecole de Technologie Supérieure, Florent AVELLANEDA Université du Québec à Montréal, Naouel Moha École de Technologie Supérieure (ETS)
16:24 6m Talk		MIRROR: A Dataset of Structural Metrics for Repackaged Android Apps FORGE Data and Benchmarking Sebastian Siedler Florida Polytechnic University, Karim Elish Florida Polytechnic University
16:30 12m Talk		MalCVE: Malware Detection and CVE Association Using Large Language Models FORGE Research Papers Eduard Andrei Cristea Norwegian University of Science and Technology, Petter Molnes Norwegian University of Science and Technology, Jingyue Li Norwegian University of Science and Technology (NTNU)
16:42 6m Talk		Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution FORGE Research Papers Chengyan Ma Singapore Management University, Jieke Shi Singapore Management University, Ruidong Han Singapore Management University, Ye Liu Singapore Management University, Yuqing Niu , David Lo Singapore Management University Pre-print
16:48 6m Talk		Jailbreaking Large Language Models via Multi-Task Embedding-based Prompt FORGE Research Papers Songrui Li Tianjin university, Hanmo You Tianjin University, Jiajun Jiang Tianjin University, li songrui

	17:00 - 17:15	Closing & FORGE 2027FORGE Program at Oceania I

Tue 14 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

09:00 - 09:10	OpenningLLM4Code at Oceania I Chair(s): Yiling Lou University of Illinois at Urbana-Champaign, Kexin Pei The University of Chicago, Prem Devanbu University of California at Davis, Lin Tan Purdue University, Lingming Zhang University of Illinois at Urbana-Champaign

09:00 10m Day opening		Openning LLM4Code

09:10 - 10:40	KeynoteLLM4Code at Oceania I

09:10 30m Talk		Beyond the Scaling Race: The Problems Academia Was Built to Solve LLM4Code Kush Jain Mistral AI
09:40 30m Talk		Hands Off the Terminal: LLM Agents that Build, Test, Analyze, and Reproduce LLM4Code Michael Pradel CISPA Helmholtz Center for Information Security
10:10 30m Talk		Towards Efficient Coding Agents LLM4Code Chao Peng ByteDance

11:00 - 11:35	Benchmarks and Evaluation of AI Coding AssistantsLLM4Code at Oceania I

11:00 10m Talk		SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories LLM4Code Chihao Shen University of Maryland, Connor Dilgren University of Maryland, Purva Chiniya University of Maryland, Luke Griffith University of Maryland, Yu Ding Google DeepMind, Yizheng Chen University of Maryland
11:10 10m Talk		RuberDuckBench: A Benchmark for AI Coding Assistants LLM4Code Ferida Mohammed Bryn Mawr College, Fatma Ayad Bryn Mawr College, Satish Chandra Meta Platforms, Inc., Petros Maniatis Google DeepMind, Elizabeth Dinellla
11:20 10m Talk		Benchmarking LLM Commit Message Generation through a Developer-centric Pairwise Preference Framework LLM4Code Lucas Almeida Aguiar State University of Ceará, Matheus Freitas State University of Ceará, Matheus Paixao State University of Ceará, Rafael Carmo Federal University of Ceará
11:30 5m Talk		Evaluating LLMs-Driven Java Code Refactoring from a Developer’s Perspective LLM4Code Javel Freitas Federal University of Ceara, Brazil, Guilherme Vaz Pereira School of Technology, PUCRS, Brazil, Lara Gabrielly Souza Batista Lima University of São Paulo (ICMC/USP), São Carlos - SP, Caio Rian de Sousa Federal University of Ceara, Brazil, Edivar FIlho Federal University of Ceara, Brazil, José Cezar de Souza Filho Université Polytechnique Hauts-de-France, Paulo Maia State University of Ceará, Carla Bezerra Federal University of Ceará (UFC)

11:35 - 12:25	Developer Experience and Human-AI ProgrammingLLM4Code at Oceania I

11:35 10m Talk		Achieving Productivity Gains with AI-based IDE features: A Journey at Google LLM4Code Maxim Tabachnyk Google, Inc., Xu Shu Google, Inc., Alexander Frömmgen Google, Inc., Pavel Sychev Google, Inc., Vahid Meimand Google, Inc., Ilia Krets Google, Inc., Stanislav Pyatykh Google, Inc., Abner Araujo Google, Inc., Kristof Molnar Google, Inc., Satish Chandra Meta Platforms, Inc.
11:45 10m Talk		Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study LLM4Code Michele Merler IBM Research, Rangeet Pan IBM Research, Rahul Krishna IBM Research, Tin Kam Ho IBM Research, Raju Pavuluri IBM T.J. Watson Research Center, Maja Vukovic IBM Research
11:55 10m Talk		Code Roulette: How Prompt Variability Affects LLM Code Generation LLM4Code Andrei Paleyes Department of Computer Science and Technology, Univesity of Cambridge, Diana Robinson University of Cambridge, UK, Radzim Sendyka University of Cambridge, Christian Cabrera University of Cambridge, Neil D. Lawrence Department of Computer Science and Technology, Univesity of Cambridge
12:05 5m Talk		English or Chinese? Investigating the Impact of Prompt Language on Large Language Models for Code Summarization LLM4Code Yijia Tang College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China, Zhiqiu Huang Nanjing University of Aeronautics and Astronautics, Jian Xie Informationization Department (Information Technology Center), Nanjing University of Aeronautics and Astronautics, Nanjing, China, Yaoshen Yu Informationization Department (Information Technology Center), Nanjing University of Aeronautics and Astronautics, Nanjing, China, Bowei Xia College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China, Enya Shen School of Software, Tsinghua University, Beijing, China, Yukun Cao School of Computer Science and Artificial Intelligence, Wuhan Textile University
12:10 10m Talk		The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution LLM4Code Norbert Tihanyi Technology Innovation Institute, Bilel Cherif Technology Innovation Institute, ABU Dhabi, UAE, Mohamed Amine Ferrag United Arab Emirates University, ABU Dhabi, UAE, Richard A. Dubniczky Eötvös Loránd University, Budapest, Hungary, Tamas Bisztray University of Oslo
12:20 10m Talk		An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code LLM4Code Sophie Weidmann University of Twente, Fernando Castor University of Twente

14:00 - 14:50	Code Generation and OptimizationLLM4Code at Oceania I

14:00 10m Talk		Towards Improving in-IDE Code Completion for Driver Development LLM4Code Batuhan Raif Karagoz Advanced Micro Devices (AMD), Mahesh Jayasankar Advanced Micro Devices (AMD), Saurabh Bodhe Advanced Micro Devices (AMD), Subhayan Roy Advanced Micro Devices (AMD), Lejin Varghese Advanced Micro Devices (AMD), Max Kiehn Advanced Micro Devices (AMD), Yonas Bedasso Advanced Micro Devices
14:10 10m Talk		Multi-task Code LLMs: Data Mix or Model Merge? LLM4Code Mingzhi Zhu Rensselaer Polytechnic Institute, Michele Merler IBM Research, Stacy Patterson Rensselaer Polytechnic Institute, Raju Pavuluri IBM T.J. Watson Research Center, Rahul Krishna IBM Research, Boris Sobolev Cisco
14:20 10m Talk		LLM-Driven SQL Remediation: Towards Safe and Explainable Code for Automated Schema Refactoring LLM4Code Antony Seabra de Medeiros Pontifical Catholic University of Rio de Janeiro, Claudio Cavalcante Pontifical Catholic University of Rio de Janeiro, Nicolaas Ruberg BNDES, Sergio Lifschitz Pontifical Catholic University of Rio de Janeiro
14:30 10m Talk		CP-Agent: Agentic Constraint Programming LLM4Code Stefan Szeider Vienna University of Technology (TU Wien)
14:40 10m Talk		Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better? LLM4Code Arastoo Zibaeirad University of North Carolina at Charlotte, Marco Vieira University of North Carolina at Charlotte

14:50 - 15:30	Testing and AnalysisLLM4Code at Oceania I

14:50 10m Talk		Statistical Independence Aware Caching for LLM Workflows LLM4Code Yihan Dai Peking University, Dimitrios Stamatios Bouras Peking University, Haoxiang Jia Peking University, Sergey Mechatev Peking University
15:00 10m Talk		An Empirical Study of C to Rust Translation using Local Large-Language Models LLM4Code Nathan Rutherford Royal Holloway, University of London, Dan O'Keeffe Royal Holloway, University of London
15:10 10m Talk		TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization LLM4Code Haonan Li University of California at Riverside, USA, Keyu Man Meta, Partha Kanuparthy Meta, Hanning Chen University of California, Irvine, Wei Sun Meta, Sreen Tallam Meta, Chenguang Zhu Meta AI, Kevin Zhu Meta, Zhiyun Qian University of California at Riverside, USA
15:20 5m Talk		A Spec-Driven Workflow for AI-Assisted Domain-Driven Development: Insights from Practice LLM4Code Jefferson de Barros Santos FGV EBAPE
15:25 5m Talk		LLM-Powered On-Demand Test Suites in Self-Graded Student Programming Assignments LLM4Code Chang Liu

16:00 - 16:40	Analysis and Optimization for AI-generated Code (Virtual Session)LLM4Code at Oceania I Chair(s): Kexin Pei The University of Chicago

16:00 10m Talk		Do LLMs Dream of Energy-Efficient Code? LLM4Code Antimo Di Bernardo Independent Researcher, Gianluca Capozzi Sapienza University of Rome, Pasquale De Rosa University of Neuchâtel, Daniele Cono D'Elia Sapienza University of Rome, Leonardo Querzoni Sapienza University of Rome, Giuseppe Antonio Di Luna Sapienza University of Rome, Valerio Schiavoni University of Neuchâtel
16:10 10m Talk		A Benchmark for Language Models in Real-World System Building LLM4Code Weilin Jin Peking University, Chenyu Zhao Nankai University, Zeshun Huang Nankai University, Chaoyun Zhang Microsoft, Qingwei Lin Microsoft, Chetan Bansal Microsoft Research, Saravan Rajmohan Microsoft, Shenglin Zhang Nankai University, Yongqian Sun Nankai University, Dan Pei Tsinghua University, Yifan Wu Peking University, Tong Jia Institute for Artificial Intelligence, Peking University, Beijing, China, Ying Li School of Software and Microelectronics, Peking University, Beijing, China, Zhonghai Wu Peking University, Minghua Ma Microsoft
16:20 10m Talk		An Automated Methodology for Generating Labeled Datasets of Semantic Errors in Code LLM4Code Mahmoud Kassem New York University Abu Dhabi, Francisco Ribeiro New York University, Abu Dhabi, Sarah Nadi New York University Abu Dhabi
16:30 10m Talk		Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empirical Study LLM4Code Shijia Dong School of Computing Science, University of Glasgow, Haoruo Zhao School of Computing Science, University of Glasgow, Paul Harvey University of Glasgow, UK

16:40 - 17:40	Agents (Virtual Session)LLM4Code at Oceania I Chair(s): Kexin Pei The University of Chicago

16:40 10m Talk		MAsFL: Data-Secure, Efficient and Accurate Fault Localization with Multi-Agent Small Language Models LLM4Code PHAM DUC DUONG National Defense Academy of Japan, HIROSHI SATO National Defense Academy of Japan, MASAO KUBO National Defense Academy of Japan
16:50 10m Talk		Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures LLM4Code Amirkia Rafiei Oskooei Yildiz Technical University / Intellica, S. Selcan Yukcu Intellica Business Intelligence, Mehmet Cevheri Bozoglan Intellica Business Intelligence, Mehmet S. Aktas Yildiz Technical University
17:00 10m Talk		RAG Against the Machine: Zero-Shot Software Vulnerabilities Classification using LLMs LLM4Code Edvin Nordqvist KTH Royal Institute of Technology, Changjie Wang KTH Royal Institute of Technology, Simone Ferlin Red Hat, Mariano Scazzariello RISE Research Institutes of Sweden, Marco Chiesa KTH Royal Institute of Technology
17:10 10m Talk		Learning Functional Equivalence via Supervised Contrastive Code-Problem Alignment LLM4Code Siu Wun Cheung Lawrence Livermore National Laboratory, Harshitha Menon Lawrence Livermore National Lab
17:20 5m Talk		Towards LLM-guided Semantic Validation of Autonomous Driving Safety Policies LLM4Code Qingzhao Zhang University of Arizona, Morley Mao University of Michigan
17:25 5m Talk		ContextPilot: Code Context Engineering with Memory-Augmented Exploration Agents LLM4Code Shuzheng Gao Chinese University of Hong Kong, Chaozheng Wang The Chinese University of Hong Kong, Shuqing Li The Chinese University of Hong Kong, Yun Peng The Chinese University of Hong Kong, Michael Lyu The Chinese University of Hong Kong
17:30 5m Talk		Continuous Benchmark Generation for Evaluating Enterprise-scale LLM Agents LLM4Code Divyanshu Saxena UT Austin, Rishikesh Maurya Microsoft, Gagan Somashekar Microsoft, Shachee Mishra Gupta Microsoft, Chetan Bansal Microsoft Research, Aditya Akella UT Austin

17:40 - 17:45	Closing and AwardLLM4Code at Oceania I

17:40 5m Day closing		Closing and Awards LLM4Code

Wed 15 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

11:00 - 12:30	Testing and Analysis 3ICSE SE In Practice (SEIP) / ICSE Research Track at Oceania I Chair(s): Yvonne Dittrich IT University of Copenhagen

11:00 15m Talk		TestifAI: Tomography-Based Testing for Deep Learning Systems ICSE Research Track Arooj Arif Northeastern University London, Tobias Hartung Northeastern University London, Elena Botoeva University of Kent, Alexandros Koliousis Northeastern University London
11:15 15m Talk		Automated Software Test Generation at Industry Scale Using a Multi-Agent Architecture and Workflow IntegrationAward Winner ICSE SE In Practice (SEIP) Matas Rastenis Uber Technologies Inc., Ben Chou Uber Technologies Inc., Shauvik Roy Choudhary Uber Technologies, Inc, René Just University of Washington
11:30 15m Talk		On the Flakiness of LLM-generated Tests for Industrial and Open-Source Database Management Systems ICSE SE In Practice (SEIP) Alexander Berndt Heidelberg University, Thomas Bach SAP, Rainer Gemulla University of Mannheim, Marcus Kessel University of Mannheim, Sebastian Baltes Heidelberg University Pre-print
11:45 15m Talk		Enabling Black-box RPC-API Testing with Multi-Agent Reinforcement Learning and LLMs: An Industry Case Study ICSE SE In Practice (SEIP) Xiaoqing Sun Alibaba Cloud, Zhou Shao Alibaba Cloud, Xiaonan Shi Alibaba Cloud, Shiliang Xiao Alibaba Cloud, Chao Ma Alibaba Cloud, Xiaobo Xue Alibaba Cloud, Jianyuan Lu Alibaba Cloud, Shize Zhang Alibaba Cloud, Enge Song Alibaba Cloud, Song Yang Alibaba Cloud, Xing Li Zhejiang University and Alibaba Cloud, Chongrong Fang Shanghai Jiao Tong University, Chunrong Fang Nanjing University, Biao Lyu Alibaba Cloud, Shunmin Zhu Hangzhou Feitian Cloud and Alibaba Cloud
12:00 15m Talk		Hamster: A Large-Scale Study and Characterization of Developer-Written Tests ICSE SE In Practice (SEIP) Rangeet Pan IBM Research, Tyler Stennett Georgia Institute of Technology, Raju Pavuluri IBM T.J. Watson Research Center, Nate Levin Georgia Institute of Technology, Alessandro Orso University of Georgia, USA, Saurabh Sinha IBM Research
12:15 15m Talk		AutoOracle: High-Quality C++ Test Oracle Generation via Data Quality-Driven and Filtering-Enabled LLMs ICSE SE In Practice (SEIP) Cong Li Samsung R&D Institute China Xi'an, Samsung Electronics, Jong-In Jang Samsung Electronics, Yuqi Zhang Samsung R&D Institute China Xi'an, Samsung Electronics, Nakwon Lee Samsung Electronics, Bin Wang , Yinghua Zhang Samsung R&D Institute China Xi'an, Samsung Electronics, Chanwook Kim Samsung Electronics, Jia Zhang Samsung R&D Institute China Xi'an, Samsung Electronics, HyunSeok Kim Samsung Electronics, Xing He Samsung R&D Institute China Xi'an, Samsung Electronics, Kangho Roh Samsung Electronics, Seongjun Ahn Samsung Electronics

14:00 - 15:30	Analytics 1ICSE SE In Practice (SEIP) / ICSE Research Track at Oceania I Chair(s): Gül Calikli University of Glasgow

14:00 15m Talk		Towards Understanding and Characterizing Vulnerabilities in Intelligent Connected Vehicles through Real-World ExploitsAward Winner ICSE Research Track Yuelin Wang College of Intelligence and Computing, Tianjin University, Yuqiao Ning China Automobile Data of Tianjin Co., Ltd. China Automotive Technology&Research Center Co.,Ltd., Yanbang Sun College of Intelligence and Computing, Tianjin University, Xiaofei Xie Singapore Management University, Zhihua Xie College of Intelligence and Computing, Tianjin University, Yang Chen China Automobile Data of Tianjin Co., Ltd. China Automotive Technology&Research Center Co.,Ltd., Zhen Guo China Automobile Data of Tianjin Co., Ltd. China Automotive Technology&Research Center Co.,Ltd., Shihao Xue China Automobile Data of Tianjin Co., Ltd. China Automotive Technology&Research Center Co.,Ltd., Junjie Wang Tianjin University, Sen Chen Nankai University
14:15 15m Talk		Defects4REST: A Benchmark of Real-World Defects to Enable Controlled Testing and Debugging Studies for REST APIs ICSE Research Track Rahil Mehta Oregon State University, Pushpak Katkhede Oregon State University, Manish Motwani Oregon State University
14:30 15m Talk		JEDI: Java Evaluation of Declarative and Imperative Queries - Benchmarking the Java Stream API ICSE Research Track Filippo Schiavio USI Lugano, Walter Binder USI Lugano
14:45 15m Talk		Characterizing GPU-accelerated Web Applications in Browsers ICSE Research Track Yudong Han Peking University, Weichen Bi Peking University, Haiyang Shen Peking University, Mugeng Liu Peking University, Ruibo Wang National University of Defense Technology, Yun Ma Peking University DOI
15:00 15m Talk		Green Software Engineering in Practice: Quantifying the Impact of Carbon Reduction Strategies in Enterprise Software ICSE SE In Practice (SEIP) Rutger Kool Vrije Universiteit Amsterdam, The Netherlands, Michiel Overeem AFAS Software, Ivano Malavolta Vrije Universiteit Amsterdam Pre-print Media Attached
15:15 15m Talk		An Empirical Study of WebAssembly Usage in Node.js ICSE Research Track Michelle Thalakottur Northeastern University, Maxwell Bernstein Recurse Center, Daniel Lehmann Google, Germany, Michael Pradel CISPA Helmholtz Center for Information Security, Frank Tip Northeastern University

16:00 - 17:30	Analytics 2ICSE SE In Practice (SEIP) / ICSE Research Track at Oceania I Chair(s): Emerson Murphy-Hill Microsoft

16:00 15m Talk		Energy-Efficient Software Development: A Multi-dimensional Empirical Analysis of Stack Overflow ICSE Research Track Bihui Jin University of Waterloo, Heng Li Polytechnique Montréal, Pengyu Nie University of Waterloo, Ying Zou Queen's University, Kingston, Ontario Pre-print
16:15 15m Talk		Towards Supporting Open Source Library Maintainers with Community-Based Analytics ICSE Research Track Rachna Raj Concordia University, Diego Elias Costa Concordia University, Canada
16:30 15m Talk		The Cost vs the Benefit of Adding an Extra Code Reviewer to Mitigate Developer Turnover through Reviewer Recommenders ICSE Research Track Mohammadali Sefidi Esfahani Concordia University, Fahimeh Hajari Concordia University, Peter Rigby Concordia University; Meta
16:45 15m Talk		Toward Efficient Package Maintenance: An Empirical Study of Patch Sharing across Four Linux Distributions ICSE Research Track Jian Peng Institute of Software, Chinese Academy of Sciences, Jiaxin Zhu Institute of Software at Chinese Academy of Sciences, Yuwei Zhang Institute of Software Chinese Academy of Sciences, Wei Chen Institute of Software at Chinese Academy of Sciences, Guoquan Wu Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences; University of Chinese Academy of Sciences Nanjing College; China Southern Power Grid, Wei Wang Institute of Software at Chinese Academy of Sciences, Jun Wei Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences
17:00 15m Talk		Evolving Trends, Patterns, and Hidden Pitfalls: Unveiling JavaScript Feature Usage in the Wild ICSE Research Track Dawei Chen Xi'an Jiaotong University, Wuxia Jin Xi'an Jiaotong University, Hui Guo Xi'an Jiaotong University, Guanlin Qiao Xi'an Jiaotong University, Peng Di Ant Group & UNSW Sydney, Ting Liu Xi'an Jiaotong University
17:15 15m Talk		What’s DAT? Three Case Studies of Measuring Software Development Productivity at Meta With Diff Authoring Time ICSE SE In Practice (SEIP) Moritz Beller Meta Platforms, Inc., USA, Amanda Park Meta Platforms, Inc., Karim Nakad Meta, Akshay Patel Meta Platforms, Inc., Sarita Mohanty Meta Platforms, Inc., Ford Garberson Meta Platforms, Inc., Henri Verroken Meta Platforms, Inc., Andrew Kennedy Meta Platforms, Inc., Ian G. Malone Meta Platforms, Inc., Vaishali Garg Meta Platforms, Inc., Pavel Avgustinov Meta Platforms, Inc.

Thu 16 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

11:00 - 12:30	Testing and Analysis 10ICSE Research Track / ICSE Demonstrations / ICSE Journal-first Papers at Oceania I Chair(s): Robert Feldt Chalmers \| University of Gothenburg

11:00 15m Talk		Seeing is Believing: Vision-driven Non-crash Functional Bug Detection for Mobile Apps ICSE Journal-first Papers Zhe Liu Institute of Software, Chinese Academy of Sciences, Cheng Li Institute of Software, Chinese Academy of Sciences, Chunyang Chen TU Munich, Junjie Wang Institute of Software at Chinese Academy of Sciences, Mengzhuo Chen Institute of Software, Chinese Academy of Sciences, Boyu Wu Institute of Software at Chinese Academy of Sciences, Yawen Wang Institute of Software at Chinese Academy of Sciences, Jun Hu Institute of Software, Chinese Academy of Sciences, Qing Wang Institute of Software at Chinese Academy of Sciences
11:15 15m Talk		PriviSense: A Frida-Based Framework for Multi-Sensor Spoofing on Android ICSE Demonstrations Ibrahim Khalilov Johns Hopkins University, Chaoran Chen University of Notre Dame, Ziang Xiao Johns Hopkins University, Tianshi Li Northeastern University, Toby Jia-Jun Li University of Notre Dame, Yaxing Yao Johns Hopkins University
11:30 15m Talk		Optimization-Aware Test Generation for Deep Learning Compilers ICSE Research Track Qingchao Shen Tianjin University, Zan Wang Tianjin University, Haoyang Ma Hong Kong University of Science and Technology, Yongqiang Tian Monash University, Lili Huang College of Intelligence and Computing, Tianjin University, Zibo Xiao College of Intelligence and Computing, Tianjin University, Junjie Chen Tianjin University, Shing-Chi Cheung Hong Kong University of Science and Technology
11:45 15m Talk		Think Outside the Box: Automating Inter-App Functionality Testing via Memory Implanting and Reasoning ICSE Research Track Mengzhuo Chen Institute of Software, Chinese Academy of Sciences, Zhe Liu Institute of Software, Chinese Academy of Sciences, Chunyang Chen TU Munich, Junjie Wang Institute of Software at Chinese Academy of Sciences, Yangguang Xue University of Chinese Academy of Sciences, Boyu Wu Institute of Software at Chinese Academy of Sciences, Libin Wu Institute of Software Chinese Academy of Sciences, Qing Wang Institute of Software at Chinese Academy of Sciences
12:00 15m Talk		Scalpel: Automotive Deep Learning Framework Testing via Assembling Model Components ICSE Research Track Yinglong Zou Nanjing University, Juan Zhai University of Massachusetts at Amherst, Chunrong Fang Nanjing University, An Guo The Hong Kong Polytechnic Universituy, Jiawei Liu State Key Laboratory for Novel Software Technology, Nanjing University, China, Zhenyu Chen Nanjing University
12:15 15m Talk		CombCT: Compiler Testing via Combinatorial Testing ICSE Research Track Chuan Luo Beihang University, Shaoke Cui Beihang University, Jiahao Yan Beihang University, Junjie Chen Tianjin University, Chenyao Suo Tianjin University, Wei Wu Central South University; Xiangjiang Laboratory, Chanjuan Liu Dalian University of Technology, Chunming Hu Beihang University

14:00 - 15:30	Analytics 3ICSE Research Track / ICSE SE In Practice (SEIP) / ICSE Journal-first Papers at Oceania I Chair(s): Maliheh Izadi Delft University of Technology

14:00 15m Talk		IntelliRadar: A Comprehensive Platform to Pinpoint Malicious Package Information from Cyber Intelligence ICSE Research Track Wenbo Guo Nanyang Technological University, Chengwei Liu Nankai University, Limin Wang Nanjing University, Yiran Zhang , Wu Jiahui , Zhengzi Xu Imperial Global Singapore, Yang Liu Nanyang Technological University Pre-print
14:15 15m Talk		A Large-Scale Empirical Study of Secret Key Leakage in Hugging Face Spaces ICSE Research Track Shaoxuan Yun Beijing University of Posts and Telecommunications, Yuchao Zhang Beijing University of Posts and Telecommunications, Zhikun Shi Beijing University of Posts and Telecommunications, Liu Wang Huazhong University of Science and Technology, Yi Wang Beijing University of Posts and Telecommunications, Yu Bai Beijing University of Posts and Telecommunications Media Attached File Attached
14:30 15m Talk		A Comprehensive Study of Concurrency Bugs in the Linux Kernel ICSE Research Track Sishuai Gong University of North Carolina at Chapel Hill, Chih-En Lin Purdue University, Kevin Wu Purdue University, Edwin Lu Purdue University, Pedro Fonseca Purdue University
14:45 15m Talk		Shaky Structures: The Wobbly World of Causal Graphs in Software Analytics ICSE Journal-first Papers Jeremy Hulse NC State, Tim Menzies North Carolina State University, Nasir Eisty University of Tennessee-Knoxville Link to publication Pre-print
15:00 15m Talk		Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios ICSE Research Track Zhi Chen Singapore Management University, Wei Ma Singapore Management University, Lingxiao Jiang Singapore Management University Pre-print
15:15 15m Talk		Learning from Change: Predictive Models for Incident Prevention in a Regulated IT Environment ICSE SE In Practice (SEIP) Eileen Kapel ING & Delft University of Technology, Jan Lennartz ING, Luís Cruz TU Delft, Diomidis Spinellis AUEB & TU Delft, Arie van Deursen TU Delft

16:00 - 17:30	Testing and Analysis 14ICSE Research Track / ICSE New Ideas and Emerging Results (NIER) at Oceania I Chair(s): Weiyi Shang University of Waterloo

16:00 15m Talk		The Undecidability of Overfitting in Automated Program Repair ICSE New Ideas and Emerging Results (NIER) Omar I. Al-Bataineh Gran Sasso Science Institute (GSSI)
16:15 15m Talk		Test Flimsiness: Characterizing Flakiness Induced by Mutation to the Code Under Test ICSE Research Track Owain Parry University of Sheffield, Gregory Kapfhammer Allegheny College, Michael Hilton Carnegie Mellon University, Phil McMinn University of Sheffield
16:30 15m Talk		Debugging Performance Issues in WebAssembly Runtimes via Mutation-based Inference ICSE Research Track Ruiying Zeng Fudan University, Shuyao Jiang The Chinese University of Hong Kong, Wenxuan Zhao Fudan University, Yangfan Zhou Fudan University
16:45 15m Talk		CoReX: Context-Aware Refinement-Based Slicing for Debugging Regression Failures ICSE Research Track Sahar Badihi University of British Columbia, Canada, Julia Rubin The University of British Columbia Pre-print
17:00 15m Talk		Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search ICSE Research Track Jiayi Zhang Nanyang Technological University, Kai Huang Technical University of Munich, Jian Zhang Beihang University, Yang Liu Nanyang Technological University, Chunyang Chen TU Munich
17:15 15m Talk		Online and Interactive Bayesian Inference Debugging ICSE Research Track Nathanael Nussbaumer TU Wien, Markus Böck TU Wien, Jürgen Cito TU Wien

Fri 17 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

11:00 - 12:30	Testing and Analysis 17ICSE Demonstrations / ICSE Journal-first Papers / ICSE New Ideas and Emerging Results (NIER) at Oceania I Chair(s): Rangeet Pan IBM Research

11:00 15m Talk		PySTAAR: An End-to-End, Extensible Framework for Automated Python Type Error Repair ICSE Demonstrations Wonseok Oh Korea University, Hyobin Park Kyungpook National University, Miryeong Kang Korea University, Seungbin Choi Kyungpook National University, Yunja Choi Kyungpook National University, Hakjoo Oh Korea University
11:15 15m Talk		FlakeSync: A Tool for Automatically Repairing Async Flaky Tests ICSE Demonstrations Nandita Jayanthi The University of Texas at Austin, Shanto Rahman The University of Texas at Austin, August Shi The University of Texas at Austin
11:30 15m Talk		The Sustainability Face of Automated Program Repair Tools ICSE Journal-first Papers Matias Martinez Universitat Politècnica de Catalunya (UPC), Silverio Martínez-Fernández UPC-BarcelonaTech, Xavier Franch Universitat Politècnica de Catalunya
11:45 15m Talk		Towards Understanding the Challenges of Bug Localization in Deep Learning Systems ICSE Journal-first Papers Sigma Jahan Dalhousie University, Mehil Shah Dalhousie University, Masud Rahman Dalhousie University
12:00 15m Talk		Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism ICSE New Ideas and Emerging Results (NIER) Lingzhe Zhang Peking University, China, Tong Jia Institute for Artificial Intelligence, Peking University, Beijing, China, Yunpeng Zhai Alibaba Group, Leyi Pan Tsinghua University, Chiming Duan Peking University, Minghua He Peking University, Pei Xiao Peking University, Ying Li School of Software and Microelectronics, Peking University, Beijing, China
12:15 15m Talk		Abductive Reasoning for Neurosymbolic Fault Localization ICSE New Ideas and Emerging Results (NIER) Minh Tam Le University of Sydney, Australia, Xi Zheng Macquarie University, Hong Jin Kang University of Sydney

14:00 - 15:30	Analytics 4ICSE Research Track / ICSE Journal-first Papers at Oceania I Chair(s): Diomidis Spinellis AUEB & TU Delft

14:00 15m Talk		Back to the Roots: Assessing Mining Techniques for Java Vulnerability-Contributing Commits ICSE Journal-first Papers Torge Hinrichs Hamburg University of Technology, Emanuele Iannone Hamburg University of Technology, Tamás Aladics University of Szeged, Peter Hegedus University of Szeged, Andrea De Lucia University of Salerno, Fabio Palomba University of Salerno, Riccardo Scandariato Hamburg University of Technology
14:15 15m Talk		Predicting the Understandability of Computational Notebooks through Code Metrics Analysis ICSE Journal-first Papers Mojtaba Mostafavi Sharif University of Technology, Alireza Asadi Department of Computer Engineering of Sharif University of Technology, Arash Asgari York University, Bardia Mohammadi Sharif University of Technology, Abbas Heydarnoori Bowling Green State University Link to publication DOI
14:30 15m Talk		How Configurable is the Linux Kernel? Analyzing Two Decades of Feature-Model History ICSE Journal-first Papers Elias Kuiter University of Magdeburg, Chico Sundermann TU Braunschweig, Thomas Thüm TU Braunschweig, Tobias Heß University of Ulm, Sebastian Krieter TU Braunschweig, Germany, Gunter Saake University of Magdeburg, Germany Pre-print
14:45 15m Talk		Breaking Strong Encapsulation: A Comprehensive Study of Java Module Abuse ICSE Research Track Yirui He University of California, Irvine, Yongbo Chen University of California, Irvine, Jessy Ayala University of California, Irvine, Yecheng Zhou University of California, Irvine, Qiran Wang University of California, Irvine, Joshua Garcia University of California, Irvine
15:00 15m Talk		Causal or Correlational? A Cohort Study on the Effects of Code Smells on Class Change- and Fault-Proneness ICSE Research Track Sabato Nocera University of Salerno, Sira Vegas Universidad Politecnica de Madrid, Giuseppe Scanniello University of Salerno, Massimiliano Di Penta University of Sannio, Italy, Natalia Juristo Universidad Politecnica de Madrid
15:15 15m Talk		Six Million (Suspected) Fake Stars on GitHub: A Growing Spiral of Popularity Contests, Spams, and Malware ICSE Research Track Hao He Carnegie Mellon University, Haoqin Yang Carnegie Mellon University, Philipp Burckhardt Socket, Inc, Alexandros Kapravelos NCSU, Bogdan Vasilescu Carnegie Mellon University, Christian Kästner Carnegie Mellon University

16:00 - 17:30	Testing and Analysis 21ICSE Research Track at Oceania I Chair(s): Seongmin Lee UCLA

16:00 15m Talk		Precise Static Identification of Ethereum Storage Variables ICSE Research Track Sifis Lagouvardos University of Athens, Yannis Bollanos Dedaub, Michael Debono Friendly Maltese Citizens, Neville Grech Dedaub Limited, Yannis Smaragdakis University of Athens Pre-print
16:15 15m Talk		D-BUNDLR: Destructing JavaScript Bundles for Effective Static Analysis ICSE Research Track Wenyuan Xu Aarhus University, Alexi Turcotte CISPA, Cristian-Alexandru Staicu CISPA Helmholtz Center for Information Security
16:30 15m Talk		PTV: Scalable Version Detection of Web Libraries and its Security Application ICSE Research Track Xinyue Liu Chongqing University, Haipeng Cai University at Buffalo, SUNY, Lukasz Ziarek University at Buffalo
16:45 15m Talk		Context-Free Grammar Inference for Complex Programming Languages in Black Box Settings ICSE Research Track Feifei Li Tsinghua Shenzhen International Graduate School, Xiao Chen University of Newcastle, xiaoyu sun The Australian National University, Xi Xiao Tsinghua University, Shaohua Wang Central University of Finance and Economics, Yong Ding School of Computer Science & lnformation Security, Guilin University of Electronic Technology, Guilin, Gusngxi, China, Sheng Wen Swinburne University of Technology, Qingli Peng Cheng Laboratory
17:00 15m Talk		LoopSCC: Summarizing Complex Multi-branch Nested Loops via Periodic Oscillation Interval ICSE Research Track Kai Zhu Institute of Information Engineering, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Haofeng Li SKLP, Institute of Computing Technology, CAS, Kuihao Yan Institute of Information Engineering, Chinese Academy of Sciences, Rongqing Wang Institute of Information Engineering, Chinese Academy of Sciences, Jiaming Guo Institute of Information Engineering, Chinese Academy of Sciences, Haoran Yang Institute of Information Engineering, Chinese Academy of Sciences, Jie Lu Institute of Computing Technology, Chinese Academy of Sciences, Lei Yu Institute of Software, Chinese Academy of Sciences, University of Chinese Academy of Sciences, China, Xiaoqi Jia Institute of Information Engineering, Chinese Academy of Sciences, Chenkai Guo Nankai University, China, Haichao Du Institute of Information Engineering, Chinese Academy of Sciences, Qingjia Huang Institute of Information Engineering, Chinese Academy of Sciences, Yamin Xie Institute of Information Engineering，Chinese Academy of Science；University of Chinese Academy of Sciences, Jing Tang Institute of Information Engineering, Chinese Academy of Sciences
17:15 15m Talk		Efficient Strong Updates For Path Sensitive Data Dependence Analysis ICSE Research Track Yiyuan Guo The Hong Kong University of Science and Technology, Ant Group, Charles Zhang Hong Kong University of Science and Technology DOI Pre-print

Sun 12 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	9:00						30						10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
Oceania I	FORGE Program + FORGE Keynotes Opening + Keynote (Prof. Zhi Jin)																								FORGE Research Papers + FORGE Data and Benchmarking Session I - Testing, Quality, and Refactoring																																				FORGE Data and Benchmarking + FORGE Research Papers Session II - Human-AI Collaboration, Multi-agent Systems, & Benchmarking																								FORGE Keynotes Industry Keynotes I

Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	9:00						30						10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
Oceania I	FORGE Program + FORGE Keynotes Keynote (Prof. Michael Pradel) + Awards																								FORGE Data and Benchmarking + FORGE Research Papers Session III - Code Generation & Migration																																				FORGE Program + FORGE Keynotes Industry Keynotes II																								FORGE Research Papers + FORGE Data and Benchmarking Session IV - Security & Privacy												FORGE Program Closing & FORGE 2027

Tue 14 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	9:00						30						10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
Oceania I	LLM4Code Openning		LLM4Code Keynote																						LLM4Code Benchmarks and Evaluation of AI Coding Assistants							LLM4Code Developer Experience and Human-AI Programming																													LLM4Code Code Generation and Optimization										LLM4Code Testing and Analysis														LLM4Code Analysis and Optimization for AI-generated Code (Virtual Session)								LLM4Code Agents (Virtual Session)												LLM4Code Closing and Award

Wed 15 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
Oceania I	ICSE SE In Practice (SEIP) + ICSE Research Track Testing and Analysis 3																																				ICSE SE In Practice (SEIP) + ICSE Research Track Analytics 1																								ICSE SE In Practice (SEIP) + ICSE Research Track Analytics 2

Thu 16 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
Oceania I	ICSE Research Track + ICSE Demonstrations + ICSE Journal-first Papers Testing and Analysis 10																																				ICSE Research Track + ICSE SE In Practice (SEIP) + ICSE Journal-first Papers Analytics 3																								ICSE Research Track + ICSE New Ideas and Emerging Results (NIER) Testing and Analysis 14

Fri 17 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
Oceania I	ICSE Demonstrations + ICSE Journal-first Papers + ICSE New Ideas and Emerging Results (NIER) Testing and Analysis 17																																				ICSE Research Track + ICSE Journal-first Papers Analytics 4																								ICSE Research Track Testing and Analysis 21

Sun 12 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45
Oceania I	FORGE Keynotes Opening Message from the Chairs 09:00 - 09:15			FORGE Keynotes Keynote: How to Enable Large Language Models to Accelerate the Process ... 09:15 - 10:30																					FORGE Research Papers Backporting in Robot Operating System: Identifying Commit Purpose and P ... 11:00 - 11:12		FORGE Research Papers PatchGPT: Multi-Agent Patch Backporting without Model Fine-Tuning 11:12 - 11:18		FORGE Research Papers From Human to Machine Refactoring: Assessing GPT-4’s Impact on Python C ... 11:18 - 11:30		FORGE Research Papers XMENTOR: A Rank-Aware Aggregation Approach for Human-Centered Explainab ... 11:30 - 11:42		FORGE Research Papers Exploring the Potential of Large Language Models in Simulink-Stateflow ... 11:42 - 11:54			FORGE Data and Benchmarking Tricky²: Towards a Benchmark for Evaluating Human and LLM Error Interac ... 11:54 - 12:00	FORGE Research Papers Reasoning about Multi-hop Fault Propagation with LLM Agents for Root Ca ... 12:00 - 12:12		FORGE Research Papers Execution-free Agentic Program Repair for Enterprise-Scale Development 12:12 - 12:24																						FORGE Research Papers Reporting LLM Prompting in Automated Software Engineering: A Guideline ... 14:00 - 14:12		FORGE Research Papers Impacts of Generative AI on Agile Teams' Productivity: A Multi-Case Lon ... 14:12 - 14:24			FORGE Research Papers Visual Loop: Bridging the Cognitive Gap in Software Development Through ... 14:24 - 14:30	FORGE Research Papers AutoReSpec: A Framework for Generating Specification using Large Langua ... 14:30 - 14:42		FORGE Research Papers CodeViz: Collaborative Multi-Agent System for Analytical and Visualizat ... 14:42 - 14:48		FORGE Data and Benchmarking SEMODS: A Validated Dataset of Open-Source Software Engineering Models 14:48 - 14:54	FORGE Data and Benchmarking Towards Comprehensive Benchmarking Infrastructure for LLMs In Software ... 14:54 - 15:00	FORGE Data and Benchmarking OmniBench-RAG: A Multi-Domain Evaluation Platform for Retrieval-Augment ... 15:00 - 15:06												FORGE Keynotes Semantics Matters: Architecting Business Context for Generative AI in S ... 16:00 - 16:45									FORGE Keynotes The Mindful IDE: From Noise to Nuance 16:45 - 17:30

Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45
Oceania I	FORGE Keynotes Keynote: Natural Language as Specification: LLM-Based Validation of Sof ... 09:00 - 10:15															FORGE Keynotes Awards session 10:15 - 10:30									FORGE Research Papers Deep Graph-Language Fusion for Structure-Aware Code Generation 11:00 - 11:06	FORGE Research Papers Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in ... 11:06 - 11:18			FORGE Research Papers Detecting and Correcting Hallucinations in LLM-Generated Code via Deter ... 11:18 - 11:24	FORGE Research Papers Code for Machines, Not Just Humans: Quantifying AI-Friendliness with Co ... 11:24 - 11:36		FORGE Data and Benchmarking VHDL-Instruct: Training Open Dataset for LLMs Benchmarking and HDL Code ... 11:36 - 11:42			FORGE Data and Benchmarking COMPASS: A Psychometrics-Guided Multi-Dimensional Benchmark for Code Ge ... 11:48 - 11:54	FORGE Research Papers A Hybrid LLM-Guided Approach to Code Migration Using API-Derived Rules 11:54 - 12:00	FORGE Research Papers An Experience Report on LLM-Based Agentic Translation from Android to i ... 12:00 - 12:12		FORGE Data and Benchmarking MiG.4: A Curated Dataset of Library Migrations in Java and Python 12:12 - 12:18		FORGE Data and Benchmarking PromiseAwait: A Dataset of JavaScript Migrations from Promises to Async ... 12:18 - 12:24																				FORGE Keynotes Lingxi - Towards Domain Knowledge Guided Repo-level Code Generation Pra ... 14:00 - 14:45									FORGE Keynotes Same Brain, Superpowers: Programming in the Age of AI 14:45 - 15:30															FORGE Research Papers PIChecker: Automatic Privacy Detector for Third Party Libraries in Andr ... 16:00 - 16:12		FORGE Research Papers DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent E ... 16:12 - 16:24			FORGE Data and Benchmarking MIRROR: A Dataset of Structural Metrics for Repackaged Android Apps 16:24 - 16:30	FORGE Research Papers MalCVE: Malware Detection and CVE Association Using Large Language Models 16:30 - 16:42		FORGE Research Papers Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Exec ... 16:42 - 16:48		FORGE Research Papers Jailbreaking Large Language Models via Multi-Task Embedding-based Prompt 16:48 - 16:54

Tue 14 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45
Oceania I	LLM4Code Openning 09:00 - 09:10		LLM4Code Beyond the Scaling Race: The Problems Academia Was Built to Solve 09:10 - 09:40						LLM4Code Hands Off the Terminal: LLM Agents that Build, Test, Analyze, and Reproduce 09:40 - 10:10						LLM4Code Towards Efficient Coding Agents 10:10 - 10:40										LLM4Code SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Re ... 11:00 - 11:10		LLM4Code RuberDuckBench: A Benchmark for AI Coding Assistants 11:10 - 11:20		LLM4Code Benchmarking LLM Commit Message Generation through a Developer-centric ... 11:20 - 11:30		LLM4Code Evaluating LLMs-Driven Java Code Refactoring from a Developer’s Perspective 11:30 - 11:35	LLM4Code Achieving Productivity Gains with AI-based IDE features: A Journey at G ... 11:35 - 11:45		LLM4Code Usage, Effects and Requirements for AI Coding Assistants in the Enterpr ... 11:45 - 11:55		LLM4Code Code Roulette: How Prompt Variability Affects LLM Code Generation 11:55 - 12:05		LLM4Code English or Chinese? Investigating the Impact of Prompt Language on Larg ... 12:05 - 12:10	LLM4Code The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable ... 12:10 - 12:20		LLM4Code An Initial Exploration of Contrastive Prompt Tuning to Generate Energy- ... 12:20 - 12:30																				LLM4Code Towards Improving in-IDE Code Completion for Driver Development 14:00 - 14:10		LLM4Code Multi-task Code LLMs: Data Mix or Model Merge? 14:10 - 14:20		LLM4Code LLM-Driven SQL Remediation: Towards Safe and Explainable Code for Autom ... 14:20 - 14:30		LLM4Code CP-Agent: Agentic Constraint Programming 14:30 - 14:40		LLM4Code Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better? 14:40 - 14:50		LLM4Code Statistical Independence Aware Caching for LLM Workflows 14:50 - 15:00		LLM4Code An Empirical Study of C to Rust Translation using Local Large-Language ... 15:00 - 15:10		LLM4Code TritonForge: Profiling-Guided Framework for Automated Triton Kernel Opt ... 15:10 - 15:20		LLM4Code A Spec-Driven Workflow for AI-Assisted Domain-Driven Development: Insig ... 15:20 - 15:25	LLM4Code LLM-Powered On-Demand Test Suites in Self-Graded Student Programming As ... 15:25 - 15:30							LLM4Code Do LLMs Dream of Energy-Efficient Code? 16:00 - 16:10		LLM4Code A Benchmark for Language Models in Real-World System Building 16:10 - 16:20		LLM4Code An Automated Methodology for Generating Labeled Datasets of Semantic Er ... 16:20 - 16:30		LLM4Code Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empi ... 16:30 - 16:40		LLM4Code MAsFL: Data-Secure, Efficient and Accurate Fault Localization with Mult ... 16:40 - 16:50		LLM4Code Natural Language Summarization Enables Multi-Repository Bug Localizatio ... 16:50 - 17:00		LLM4Code RAG Against the Machine: Zero-Shot Software Vulnerabilities Classificat ... 17:00 - 17:10		LLM4Code Learning Functional Equivalence via Supervised Contrastive Code-Problem ... 17:10 - 17:20		LLM4Code Towards LLM-guided Semantic Validation of Autonomous Driving Safety Pol ... 17:20 - 17:25	LLM4Code ContextPilot: Code Context Engineering with Memory-Augmented Exploratio ... 17:25 - 17:30	LLM4Code Continuous Benchmark Generation for Evaluating Enterprise-scale LLM Agents 17:30 - 17:35		LLM4Code Closing and Awards 17:40 - 17:45

Wed 15 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45
Oceania I	ICSE Research Track TestifAI: Tomography-Based Testing for Deep Learning Systems 11:00 - 11:15			ICSE SE In Practice (SEIP)Award Winner Automated Software Test Generation at Industry Scale Using a Multi-Agen ... 11:15 - 11:30			ICSE SE In Practice (SEIP) On the Flakiness of LLM-generated Tests for Industrial and Open-Source ... 11:30 - 11:45			ICSE SE In Practice (SEIP) Enabling Black-box RPC-API Testing with Multi-Agent Reinforcement Learn ... 11:45 - 12:00			ICSE SE In Practice (SEIP) Hamster: A Large-Scale Study and Characterization of Developer-Written ... 12:00 - 12:15			ICSE SE In Practice (SEIP) AutoOracle: High-Quality C++ Test Oracle Generation via Data Quality-Dr ... 12:15 - 12:30																					ICSE Research TrackAward Winner Towards Understanding and Characterizing Vulnerabilities in Intelligent ... 14:00 - 14:15			ICSE Research Track Defects4REST: A Benchmark of Real-World Defects to Enable Controlled Te ... 14:15 - 14:30			ICSE Research Track JEDI: Java Evaluation of Declarative and Imperative Queries - Benchmark ... 14:30 - 14:45			ICSE Research Track Characterizing GPU-accelerated Web Applications in Browsers 14:45 - 15:00			ICSE SE In Practice (SEIP) Green Software Engineering in Practice: Quantifying the Impact of Carbo ... 15:00 - 15:15			ICSE Research Track An Empirical Study of WebAssembly Usage in Node.js 15:15 - 15:30									ICSE Research Track Energy-Efficient Software Development: A Multi-dimensional Empirical An ... 16:00 - 16:15			ICSE Research Track Towards Supporting Open Source Library Maintainers with Community-Based ... 16:15 - 16:30			ICSE Research Track The Cost vs the Benefit of Adding an Extra Code Reviewer to Mitigate De ... 16:30 - 16:45			ICSE Research Track Toward Efficient Package Maintenance: An Empirical Study of Patch Shari ... 16:45 - 17:00			ICSE Research Track Evolving Trends, Patterns, and Hidden Pitfalls: Unveiling JavaScript Fe ... 17:00 - 17:15			ICSE SE In Practice (SEIP) What’s DAT? Three Case Studies of Measuring Software Development Produc ... 17:15 - 17:30

Thu 16 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45
Oceania I	ICSE Journal-first Papers Seeing is Believing: Vision-driven Non-crash Functional Bug Detection f ... 11:00 - 11:15			ICSE Demonstrations PriviSense: A Frida-Based Framework for Multi-Sensor Spoofing on Android 11:15 - 11:30			ICSE Research Track Optimization-Aware Test Generation for Deep Learning Compilers 11:30 - 11:45			ICSE Research Track Think Outside the Box: Automating Inter-App Functionality Testing via M ... 11:45 - 12:00			ICSE Research Track Scalpel: Automotive Deep Learning Framework Testing via Assembling Mode ... 12:00 - 12:15			ICSE Research Track CombCT: Compiler Testing via Combinatorial Testing 12:15 - 12:30																					ICSE Research Track IntelliRadar: A Comprehensive Platform to Pinpoint Malicious Package In ... 14:00 - 14:15			ICSE Research Track A Large-Scale Empirical Study of Secret Key Leakage in Hugging Face Spaces 14:15 - 14:30			ICSE Research Track A Comprehensive Study of Concurrency Bugs in the Linux Kernel 14:30 - 14:45			ICSE Journal-first Papers Shaky Structures: The Wobbly World of Causal Graphs in Software Analytics 14:45 - 15:00			ICSE Research Track Beyond Final Code: A Process-Oriented Error Analysis of Software Develo ... 15:00 - 15:15			ICSE SE In Practice (SEIP) Learning from Change: Predictive Models for Incident Prevention in a Re ... 15:15 - 15:30									ICSE New Ideas and Emerging Results (NIER) The Undecidability of Overfitting in Automated Program Repair 16:00 - 16:15			ICSE Research Track Test Flimsiness: Characterizing Flakiness Induced by Mutation to the Co ... 16:15 - 16:30			ICSE Research Track Debugging Performance Issues in WebAssembly Runtimes via Mutation-based ... 16:30 - 16:45			ICSE Research Track CoReX: Context-Aware Refinement-Based Slicing for Debugging Regression ... 16:45 - 17:00			ICSE Research Track Repair Ingredients Are All You Need: Improving Large Language Model-Bas ... 17:00 - 17:15			ICSE Research Track Online and Interactive Bayesian Inference Debugging 17:15 - 17:30

Fri 17 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change


Room	11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45
Oceania I	ICSE Demonstrations PySTAAR: An End-to-End, Extensible Framework for Automated Python Type ... 11:00 - 11:15			ICSE Demonstrations FlakeSync: A Tool for Automatically Repairing Async Flaky Tests 11:15 - 11:30			ICSE Journal-first Papers The Sustainability Face of Automated Program Repair Tools 11:30 - 11:45			ICSE Journal-first Papers Towards Understanding the Challenges of Bug Localization in Deep Learni ... 11:45 - 12:00			ICSE New Ideas and Emerging Results (NIER) Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservi ... 12:00 - 12:15			ICSE New Ideas and Emerging Results (NIER) Abductive Reasoning for Neurosymbolic Fault Localization 12:15 - 12:30																					ICSE Journal-first Papers Back to the Roots: Assessing Mining Techniques for Java Vulnerability-C ... 14:00 - 14:15			ICSE Journal-first Papers Predicting the Understandability of Computational Notebooks through Cod ... 14:15 - 14:30			ICSE Journal-first Papers How Configurable is the Linux Kernel? Analyzing Two Decades of Feature- ... 14:30 - 14:45			ICSE Research Track Breaking Strong Encapsulation: A Comprehensive Study of Java Module Abuse 14:45 - 15:00			ICSE Research Track Causal or Correlational? A Cohort Study on the Effects of Code Smells o ... 15:00 - 15:15			ICSE Research Track Six Million (Suspected) Fake Stars on GitHub: A Growing Spiral of Popul ... 15:15 - 15:30									ICSE Research Track Precise Static Identification of Ethereum Storage Variables 16:00 - 16:15			ICSE Research Track D-BUNDLR: Destructing JavaScript Bundles for Effective Static Analysis 16:15 - 16:30			ICSE Research Track PTV: Scalable Version Detection of Web Libraries and its Security Appli ... 16:30 - 16:45			ICSE Research Track Context-Free Grammar Inference for Complex Programming Languages in Bla ... 16:45 - 17:00			ICSE Research Track LoopSCC: Summarizing Complex Multi-branch Nested Loops via Periodic Osc ... 17:00 - 17:15			ICSE Research Track Efficient Strong Updates For Path Sensitive Data Dependence Analysis 17:15 - 17:30

Room information: Oceania I

This program is tentative and subject to change.

Program Display Configuration

Sun 12 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Mon 13 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Tue 14 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Wed 15 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Thu 16 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Fri 17 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Sun 12 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

FORGE Program + FORGE Keynotes

FORGE Research Papers + FORGE Data and Benchmarking

FORGE Data and Benchmarking + FORGE Research Papers

FORGE Keynotes

Mon 13 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

FORGE Program + FORGE Keynotes

FORGE Data and Benchmarking + FORGE Research Papers

FORGE Program + FORGE Keynotes

FORGE Research Papers + FORGE Data and Benchmarking

FORGE Program

Tue 14 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

LLM4Code

LLM4Code

LLM4Code

LLM4Code

LLM4Code

LLM4Code

LLM4Code

LLM4Code

LLM4Code

Wed 15 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

ICSE SE In Practice (SEIP) + ICSE Research Track

ICSE SE In Practice (SEIP) + ICSE Research Track

ICSE SE In Practice (SEIP) + ICSE Research Track

Thu 16 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

ICSE Research Track + ICSE Demonstrations + ICSE Journal-first Papers

ICSE Research Track + ICSE SE In Practice (SEIP) + ICSE Journal-first Papers

ICSE Research Track + ICSE New Ideas and Emerging Results (NIER)

Fri 17 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

ICSE Demonstrations + ICSE Journal-first Papers + ICSE New Ideas and Emerging Results (NIER)

ICSE Research Track + ICSE Journal-first Papers

ICSE Research Track

Sun 12 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Mon 13 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Tue 14 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Wed 15 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Thu 16 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Fri 17 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change

Sun 12 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Tue 14 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Wed 15 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Thu 16 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Fri 17 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Sun 12 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Tue 14 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Wed 15 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Thu 16 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Fri 17 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Sun 12 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Mon 13 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Tue 14 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Wed 15 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Thu 16 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change

Fri 17 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change