Asia I - ICSE 2026

VenueWindsor Convention Center and Hotels

Room nameAsia 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

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

11:00 - 12:30	AI for Software Engineering 1Research Track / SE In Practice (SEIP) at Asia I Chair(s): Italo Santos University of Hawai‘i at Mānoa

11:00 15m Talk		CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model Editing Research Track Shuhan Liu Zhejiang University, Xing Hu Zhejiang University, Kerui Huang , Xiaohu Yang Zhejiang University, David Lo Singapore Management University, Xin Xia Zhejiang University
11:15 15m Talk		Repairing LLM Executions for Secure Automatic Programming Research Track Ali El Husseini National University of Singapore, Yacine Izza National University of Singapore, Blaise Genest IPAL - CNRS - CNRS@CREATE, Abhik Roychoudhury National University of Singapore
11:30 15m Talk		SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-Aware Fine-Tuning Research Track Fang Liu Beihang University, Simiao Liu Beihang University, Yinghao Zhu Beihang University, Xiaoli Lian Beihang University, China, Li Zhang Beihang University Pre-print
11:45 15m Talk		Find My Code Twin: Improving SNIPPET SEARCH Performance Using LLMs in Practice SE In Practice (SEIP) Seokjun Ko Samsung Electronics Co., Eunbi Jang AI Center, Samsung Electronics, Dahyeon Choi AI Center, Samsung Electronics, daeha ryu Innovation Center, Samsung Electronics, jinyoung park Innovation Center, Samsung Electronics, changseo park Innovation Center, Samsung Electronics DOI Media Attached
12:00 15m Talk		Fixing Security Vulnerabilities with Agentic AI in OSS-Fuzz SE In Practice (SEIP) Yuntong Zhang National University of Singapore, Jiawei Wang University of Southern California, Dominic Berzin National University of Singapore, Martin Mirchev SonarSource, Abhik Roychoudhury National University of Singapore
12:15 15m Talk		EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation SE In Practice (SEIP) Chaofan Wang Shanghai Jiao Tong University, Tingrui Yu Shanghai Jiao Tong University, Chen Xie Shanghai Jiao Tong University, Jie Wang Huawei Technologies Co., Ltd, Dong Chen Huawei Technologies Co., Ltd, Wenrui Zhang Huawei Technologies Co., Ltd, Yuling Shi Shanghai Jiao Tong University, Xiaodong Gu Shanghai Jiao Tong University, Beijun Shen Shanghai Jiao Tong University

14:00 - 15:30	AI for Software Engineering 4Research Track / SE In Practice (SEIP) at Asia I Chair(s): Romain Robbes CNRS, LaBRI, University of Bordeaux

14:00 15m Talk		TestWeaver: Execution-aware, Feedback-driven Regression Testing Generation with Large Language Models Research Track Cuong Chi Le The University of Texas at Dallas, Cuong Duc Van FPT Software AI Center, Tung Duy Vu VinUniversity, Minh V. T. Pham FPT Software AI Center, Hoang Nhat Phan Nanyang Technological University, Huy N. Phan FPT Software AI Center, Tien N. Nguyen University of Texas at Dallas
14:15 15m Talk		RealityCraft: Automated Synthesis of Extended Reality Device Interaction Scripts from Natural Language Instructions Research Track Shuqing Li The Chinese University of Hong Kong, Yun Peng The Chinese University of Hong Kong, Yige Chen Southern University of Science and Technology, Dingyuan Xue Southern University of Science and Technology, Yepang Liu Southern University of Science and Technology, Michael Lyu The Chinese University of Hong Kong
14:30 15m Talk		Heterogeneous Prompting and Execution Feedback for SWE Issue Test Generation and Selection Research Track Toufique Ahmed IBM, Jatin Ganhotra IBM Research, Avraham Shinnar IBM Research, Martin Hirzel IBM Research Pre-print
14:45 15m Talk		LLM Test Generation via Iterative Hybrid Program Analysis Research Track Sijia Gu The University of British Columbia, Noor Nashid University of British Columbia, Ali Mesbah University of British Columbia
15:00 15m Talk		Scaling Security Testing by Addressing the Reachability Gap Research Track Gaetano Sapia Max Planck Institute for Security and Privacy (MPI-SP), Marcel Böhme MPI for Security and Privacy
15:15 15m Talk		XBIDetective: Leveraging Vision Language Models for Identifying Cross-Browser Visual Inconsistencies SE In Practice (SEIP) Balreet Grewal University of Alberta, James Graham Mozilla Corporation, Jeff Muizelaar Mozilla Corporation, Jan Honza Odvarko Independent Researcher, Suhaib Mujahid Mozilla, Marco Castelluccio Mozilla, Cor-Paul Bezemer University of Alberta Pre-print

16:00 - 17:30	AI for Software Engineering 7SE In Practice (SEIP) at Asia I Chair(s): Stan Kurkovsky Central Connecticut State University

16:00 15m Talk		From Rules to LLM-Enhanced Templates: A Hybrid ALPG Code Generation System SE In Practice (SEIP) Sanghyeok Park Sungkyunkwan University, Samsung Electronics, Sungjae Hwang Sungkyunkwan University, Simon S. Woo Sungkyunkwan University
16:15 15m Talk		Enterprise-Scale COBOL-to-Java Translation: LLMs Augmented with Program Analysis SE In Practice (SEIP) Venkatesan Chakaravarthy IBM Research - India, Anamitra Roy Choudhury IBM, Dinesh Garg IBM Research, India, Vini Kanvar IBM Research, Shivmaran Pandian IBM Research - India, Aditya Raghuvanshi International Institute of Information Technology - Hyderabad, Yogish Sabharwal IBM Research - India, Amith Singhee IBM Research, India
16:30 15m Talk		Smart Paste: Automatically Fixing Copy/Paste for Google Developers SE In Practice (SEIP) Vincent Nguyen Google, Guilherme Herzog Google, José Pablo Cambronero Google, USA, Marcus Revaj Google, Aditya Kini Google, Alexander Frömmgen Google, Inc., Maxim Tabachnyk Google, Inc. DOI Pre-print
16:45 15m Talk		Utilizing LLMs for Industrial Process Automation: A Case Study on Modifying RAPID Programs SE In Practice (SEIP) Salim Fares University of Passau, Faculty of Computer Science and Mathematics, Chair of AI Engineering, Steffen Herbold University of Passau DOI Pre-print
17:00 15m Talk		Less Effort, More Productivity: Lessons Learned from Developing Millions of Lines of Code with Large Language Model SE In Practice (SEIP) Yu Duan Xidian University, Daiyang Zhang Xidian University, Zhiping Jiang Xidian University, Zhuoyu Xie Xidian University, Yiming Liu Xidian University, Yueshen Xu Xidian University, Rui Li , Di Cui Xidian University
17:15 15m Talk		WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsApp SE In Practice (SEIP) Ke Mao Meta, Timotej Kapus Meta, Cons Ahs Meta, Matteo Marescotti Meta, Daniel Ip Meta, Ákos Hajdu Meta, Sopot Cela Meta, Aparup Banerjee Meta

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

11:00 - 12:30	AI for Software Engineering 10Research Track / Journal-first Papers at Asia I Chair(s): Fabio Marcos De Abreu Santos Colorado State University, USA

11:00 15m Talk		FlipFlop: A Static Analysis-based Energy Optimization Framework for GPU Kernels Research Track Saurabhsingh Rajput Dalhousie University, Alexander Brandt Dalhousie University, Vadim Elisseev IBM, Tushar Sharma Dalhousie University
11:15 15m Talk		Portable Power Modeling with Transfer Learning on JVM-Based Applications Research Track Joseph Raskind SUNY Binghamton, Timur Babakol SUNY Binghamton, USA, Yu David Liu SUNY Binghamton
11:30 15m Talk		End-to-End Model Generation with Large Language Models for Adaptive IoT Application Deployment Research Track ZHENYU WEN Zhejiang University of Technology, Jintao Feng Zhejiang University of Technology, Yao Nanjie Zhejiang University of Technology, Di Wu University of Central Florida, Cong Wang Zhejiang University, China, Mincheng Wu Zhejiang University of Technology, Jianbin Qin Shenzhen Institute of Computing Sciences, Shenzhen University, Shibo He Zhejiang University
11:45 15m Talk		Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead Journal-first Papers Jieke Shi Singapore Management University, Zhou Yang University of Alberta, Alberta Machine Intelligence Institute , David Lo Singapore Management University
12:00 15m Talk		An Empirical Study of Knowledge Distillation for Code Understanding Tasks Research Track Ruiqi Wang Harbin Institute of Technology, Shenzhen, Zezhou Yang , Cuiyun Gao Harbin Institute of Technology, Shenzhen, Xin Xia Zhejiang University, Qing Liao Harbin Institute of Technology Pre-print
12:15 15m Talk		Generating Energy-Efficient Code via Large-Language Models - Where are we now? Research Track Radu Apsan Vrije Universiteit Amsterdam, The Netherlands, Vincenzo Stoico Vrije Universiteit Amsterdam, Michel Albonico Federal University of Technology, Paraná (UTFPR), Rudra Dhar IIIT Hyderabad, Karthik Vaidhyanathan IIIT Hyderabad, Ivano Malavolta Vrije Universiteit Amsterdam Pre-print Media Attached

14:00 - 15:30	AI for Software Engineering 13SE In Practice (SEIP) / Research Track at Asia I Chair(s): Dalal Alrajeh Imperial College London

14:00 15m Talk		Improving Code Generation via Small Language Model-as-a-judge Research Track Giuseppe Crupi Università della Svizzera italiana, Rosalia Tufano Università della Svizzera Italiana, Gabriele Bavota Software Institute @ Università della Svizzera Italiana Pre-print
14:15 15m Talk		Think Like Human Developers: Harnessing Community Knowledge for Structured Code ReasoningAward Winner Research Track Chengran Yang Singapore Management University, Singapore, Zhensu Sun Singapore Management University, Hong Jin Kang University of Sydney, Jieke Shi Singapore Management University, David Lo Singapore Management University
14:30 15m Talk		On LLMs’ Internal Representation of Code Correctness Research Track Francisco Ribeiro New York University Abu Dhabi, Claudio Spiess University of California, Davis, Prem Devanbu University of California at Davis, Sarah Nadi New York University Abu Dhabi
14:45 15m Talk		Write Your Own Code Checker: An Automated Test-Driven Checker Development Approach with LLMs Research Track Jun Liu Institute of Software, Chinese Academy of Sciences, Yuanyuan Xie Institute of Software, Chinese Academy of Sciences, Jiwei Yan Institute of Software at Chinese Academy of Sciences, Jinhao Huang Institute of Software, Chinese Academy of Sciences, Jun Yan Institute of Software, Chinese Academy of Sciences, Jian Zhang Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences
15:00 15m Talk		RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian SE In Practice (SEIP) Kla Tantithamthavorn Monash University, Yaotian Zou Atlassian, Andy Wong Atlassian, Michael Gupta Atlassian, Zhe Wang Atlassian, Mike Buller Atlassian, Ryan Jiang Atlassian, Matthew Watson Atlassian, Minwoo Jeong Atlassian, Kun Chen Atlassian, Ming Wu Atlassian Pre-print
15:15 15m Talk		Spec2Control: Automating PLC/DCS Control-Logic Engineering from Natural Language Requirements with LLMs - A Multi-Plant Evaluation SE In Practice (SEIP) Heiko Koziolek ABB Corporate Research, Thilo Braun ABB, Virendra Ashiwal ABB Research, Sofia Linsbauer ABB Research, Marthe Ahlgreen Hansen ABB, Karoline Grotterud ABB

16:00 - 17:30	AI for Software Engineering 16Research Track at Asia I Chair(s): Karthik Vaidhyanathan IIIT Hyderabad

16:00 15m Talk		An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software Research Track Sina Gogani Khiabani University of Illinois Chicago, Ashutosh Trivedi University of Colorado Boulder, Diptikalyan Saha IBM Research, Saeid Tizpaz-Niari University of Illinois Chicago
16:15 15m Talk		RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring Research Track Khouloud Oueslati Polytechnique Montréal, Canada, Maxime Lamothe Polytechnique Montreal, Foutse Khomh Polytechnique Montréal
16:30 15m Talk		ProofCoop: Collaborative Automated Formal Verification Research Track Zhanna Kaufman University of Massachusetts, Emily First Rutgers University, Alex Sanchez-Stern d model, Kyle Thompson University of California, San Diego, Sorin Lerner University of California at San Diego, Yuriy Brun University of Massachusetts DOI Pre-print
16:45 15m Talk		Unified Software Engineering agent as AI Software Engineer Research Track Leonhard Applis National University of Singapore, Yuntong Zhang National University of Singapore, Shanchao Liang Purdue University, USA, Nan Jiang Purdue University, Lin Tan Purdue University, Abhik Roychoudhury National University of Singapore
17:00 15m Talk		Argus: A Multi-agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships Research Track Bin Wang , Hui Li Xiamen University, Liyang Zhang University of Electronic Science and Technology of China, Qijia Zhuang University of Electronic Science and Technology of China, Ao Yang Peking University, Dong Zhang Tencent Security Platform Department, Xijun Luo Tencent Security Platform Department, Bing Lin China Unicom(Guangdong) Industrial Internet Co., Ltd
17:15 15m Talk		MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming Research Track Zixiao Zhao , Jing Sun School of Computer Science, University of Auckland, Zhe Hou Griffith University, Wei Zhiyuan Beijing Institute of Technology, ChengHao Cai Suzhou Industrial Park Monash Research Institute of Science and Technology, Miao Qiao University of Auckland, Jin Song Dong National University of Singapore

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

11:00 - 12:30	AI for Software Engineering 20New Ideas and Emerging Results (NIER) / Research Track / Journal-first Papers at Asia I Chair(s): Ipek Ozkaya Carnegie Mellon University

11:00 15m Talk		Is Hyper-Parameter Optimization Different for Software Analytics? Journal-first Papers Rahul Yedida LexisNexis, Tim Menzies North Carolina State University Link to publication Pre-print
11:15 15m Talk		On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization Journal-first Papers Giuseppe Crupi Università della Svizzera italiana, Rosalia Tufano Università della Svizzera Italiana, Alejandro Velasco William & Mary, Antonio Mastropaolo William and Mary, USA, Denys Poshyvanyk William & Mary, Gabriele Bavota Software Institute @ Università della Svizzera Italiana
11:30 15m Talk		A Catalog of Data Smells for Coding Tasks Journal-first Papers Antonio Vitale Politecnico di Torino, University of Molise, Rocco Oliveto University of Molise, Simone Scalabrino University of Molise Link to publication
11:45 15m Talk		Towards Automating Domain-Specific Data Generation for Text-to-SQL: A Comprehensive Approach Journal-first Papers Salmane Chafik UM6P College of Computing, Saad Ezzini King Fahad University of Petroleum and Minerals, Ismail Berrada UM6P College of Computing
12:00 15m Talk		Empirical and Sustainability Aspects of Software Engineering Research in the Era of Large Language Models: A Reflection New Ideas and Emerging Results (NIER) David Williams University College London, Maria Kechagia National and Kapodistrian University of Athens, Max Hort Simula Research Laboratory, Aldeida Aleti Monash University, Justyna Petke University College London, Federica Sarro University College London
12:15 15m Talk		FORGE: An LLM-driven Framework for Large-Scale Smart Contract Vulnerability Dataset Construction Research Track Jiachi Chen Sun Yat-sen University, Yiming Shen Sun Yat-sen University, Jiashuo Zhang Peking University, China, Zihao Li Hong Kong Polytechnic University, John Grundy Monash University, Zhenzhe Shao Sun Yat-sen University, Yanlin Wang Sun Yat-sen University, Jiashui Wang Zhejiang University, Ting Chen University of Electronic Science and Technology of China, Zibin Zheng Sun Yat-sen University Pre-print

14:00 - 15:30	AI for Software Engineering 23Research Track / Demonstrations / Journal-first Papers at Asia I Chair(s): Wesley K.G. Assunção North Carolina State University

14:00 15m Talk		CI-Bench: A Framework for Evaluating Large Language Model Tools on CI Failures Demonstrations Raian Latif Nabil University of California, Davis, Hao-Nan Zhu University of California, Davis, Cindy Rubio-González University of California at Davis
14:15 15m Talk		Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation Journal-first Papers Fernando Vallecillos Ruiz Simula Research Laboratory, Anastasiia Grishina Simula Research Laboratory, Max Hort Simula Research Laboratory, Leon Moonen Simula Research Laboratory
14:30 15m Talk		XRFix: Exploring Performance Bug Repair of Extended Reality Applications with Large Language Models Research Track Jingwen Wu Department of Computer Science, Hong Kong Baptist University, Hanyang Guo School of Software Engineering, Sun Yat-sen University, Hong-Ning Dai Department of Computer Science, Hong Kong Baptist University, Xiapu Luo Hong Kong Polytechnic University DOI Pre-print
14:45 15m Talk		Synthetic Repo-level Bug Dataset for Training Automated Program Repair ModelsAward Winner Research Track Minh V. T. Pham FPT Software AI Center, Huy N. Phan FPT Software AI Center, Hoang Nhat Phan Nanyang Technological University, Cuong Chi Le The University of Texas at Dallas, Tien N. Nguyen University of Texas at Dallas, Nghi D. Q. Bui Google Research
15:00 15m Talk		PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates Research Track Yuan-An Xiao Peking University, Weixuan Wang Peking University, Dong Liu Center Research Institute, ZTE Coporation, China, Junwei Zhou Center Research Institute, ZTE Coporation, China, Shengyu Cheng ZTE Corporation, Yingfei Xiong Peking University Pre-print
15:15 15m Talk		Input Reduction Enhanced LLM-based Program Repair Research Track Boyang Yang Yanshan University, Luyao Ren Peking University, Xin Yin Zhejiang University, Jiadong Ren Yanshan University, Haoye Tian Aalto University, Shunfu Jin Yanshan University DOI Pre-print

16:00 - 17:30	AI for Software Engineering 26Research Track / Demonstrations / New Ideas and Emerging Results (NIER) at Asia I Chair(s): Jiakun Liu Harbin Institute of Technology

16:00 15m Talk		AdapTrack: Constrained Decoding without Distorting LLM's Output Intent Research Track Yongmin Li Peking University, Jia Li Tsinghua University, Ge Li Peking University, Zhi Jin Peking University, Wuhan University
16:15 15m Talk		Evaluating Generated Commit Messages with Large Language ModelsAward Winner Research Track Qunhong Zeng Beijing Institute of Technology, Yuxia Zhang Beijing Institute of Technology, Zexiong Ma Peking University, Bo Jiang Bytedance Network Technology, Ningyuan Sun ByteDance, Klaas-Jan Stol Lero; University College Cork; SINTEF Digital , Xingyu Mou Beijing Institute of Technology, Hui Liu Beijing Institute of Technology Pre-print
16:30 15m Talk		Automating Just-In-Time Python Type Annotation UpdatingAward Winner Research Track Zhipeng Xue Zhejiang University, Zhipeng Gao Shanghai Institute for Advanced Study - Zhejiang University, Xing Hu Zhejiang University, Jingyuan Chen Zhejiang University, Xin Xia Zhejiang University, Shanping Li Zhejiang University
16:45 15m Talk		Unveiling the Potential of Diffusion Large Language Models in Software Engineering Tasks: An Empirical Study New Ideas and Emerging Results (NIER) Jingyao Zhang Xi'an Jiaotong-Liverpool University, Li Tianlin NTU, Xiaoyu Zhang Nanyang Technological University, Singapore, Qiang Hu Tianjin University, Bin Shi Xi'an Jiaotong University
17:00 15m Talk		Enhancing LLM Code Generation with Ensembles: A Similarity-Based Selection Approach Research Track Tarek Mahmud Texas State University, Bin Duan University of Queensland, Corina S. Păsăreanu Carnegie Mellon University; NASA Ames, Guowei Yang University of Queensland
17:15 15m Talk		Code4MeV2: a Research-oriented Code-completion Platform Demonstrations Roham Koohestani Delft University of Technology, Parham Bateni Delft University of Technology, Aydin Ebrahimi Delft University of Technology, Behdad Etezadi Delft University of Technology, Kiarash Karimi Delft University of Technology, Mali Izadi TU Delft

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
Asia I	Research Track + SE In Practice (SEIP) AI for Software Engineering 1																																				Research Track + SE In Practice (SEIP) AI for Software Engineering 4																								SE In Practice (SEIP) AI for Software Engineering 7

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
Asia I	Research Track + Journal-first Papers AI for Software Engineering 10																																				SE In Practice (SEIP) + Research Track AI for Software Engineering 13																								Research Track AI for Software Engineering 16

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
Asia I	New Ideas and Emerging Results (NIER) + Research Track + Journal-first Papers AI for Software Engineering 20																																				Research Track + Demonstrations + Journal-first Papers AI for Software Engineering 23																								Research Track + Demonstrations + New Ideas and Emerging Results (NIER) AI for Software Engineering 26

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
Asia I	ICSE Research Track CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model Editing 11:00 - 11:15			ICSE Research Track Repairing LLM Executions for Secure Automatic Programming 11:15 - 11:30			ICSE Research Track SecureReviewer: Enhancing Large Language Models for Secure Code Review ... 11:30 - 11:45			ICSE SE In Practice (SEIP) Find My Code Twin: Improving SNIPPET SEARCH Performance Using LLMs in P ... 11:45 - 12:00			ICSE SE In Practice (SEIP) Fixing Security Vulnerabilities with Agentic AI in OSS-Fuzz 12:00 - 12:15			ICSE SE In Practice (SEIP) EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Tran ... 12:15 - 12:30																					ICSE Research Track TestWeaver: Execution-aware, Feedback-driven Regression Testing Generat ... 14:00 - 14:15			ICSE Research Track RealityCraft: Automated Synthesis of Extended Reality Device Interactio ... 14:15 - 14:30			ICSE Research Track Heterogeneous Prompting and Execution Feedback for SWE Issue Test Gener ... 14:30 - 14:45			ICSE Research Track LLM Test Generation via Iterative Hybrid Program Analysis 14:45 - 15:00			ICSE Research Track Scaling Security Testing by Addressing the Reachability Gap 15:00 - 15:15			ICSE SE In Practice (SEIP) XBIDetective: Leveraging Vision Language Models for Identifying Cross-B ... 15:15 - 15:30									ICSE SE In Practice (SEIP) From Rules to LLM-Enhanced Templates: A Hybrid ALPG Code Generation System 16:00 - 16:15			ICSE SE In Practice (SEIP) Enterprise-Scale COBOL-to-Java Translation: LLMs Augmented with Program ... 16:15 - 16:30			ICSE SE In Practice (SEIP) Smart Paste: Automatically Fixing Copy/Paste for Google Developers 16:30 - 16:45			ICSE SE In Practice (SEIP) Utilizing LLMs for Industrial Process Automation: A Case Study on Modif ... 16:45 - 17:00			ICSE SE In Practice (SEIP) Less Effort, More Productivity: Lessons Learned from Developing Million ... 17:00 - 17:15			ICSE SE In Practice (SEIP) WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at Wha ... 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
Asia I	ICSE Research Track FlipFlop: A Static Analysis-based Energy Optimization Framework for GPU ... 11:00 - 11:15			ICSE Research Track Portable Power Modeling with Transfer Learning on JVM-Based Applications 11:15 - 11:30			ICSE Research Track End-to-End Model Generation with Large Language Models for Adaptive IoT ... 11:30 - 11:45			ICSE Journal-first Papers Efficient and Green Large Language Models for Software Engineering: Lit ... 11:45 - 12:00			ICSE Research Track An Empirical Study of Knowledge Distillation for Code Understanding Tasks 12:00 - 12:15			ICSE Research Track Generating Energy-Efficient Code via Large-Language Models - Where are ... 12:15 - 12:30																					ICSE Research Track Improving Code Generation via Small Language Model-as-a-judge 14:00 - 14:15			ICSE Research TrackAward Winner Think Like Human Developers: Harnessing Community Knowledge for Structu ... 14:15 - 14:30			ICSE Research Track On LLMs’ Internal Representation of Code Correctness 14:30 - 14:45			ICSE Research Track Write Your Own Code Checker: An Automated Test-Driven Checker Developme ... 14:45 - 15:00			ICSE SE In Practice (SEIP) RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Cod ... 15:00 - 15:15			ICSE SE In Practice (SEIP) Spec2Control: Automating PLC/DCS Control-Logic Engineering from Natural ... 15:15 - 15:30									ICSE Research Track An LLM Agentic Approach for Legal-Critical Software: A Case Study for T ... 16:00 - 16:15			ICSE Research Track RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refa ... 16:15 - 16:30			ICSE Research Track ProofCoop: Collaborative Automated Formal Verification 16:30 - 16:45			ICSE Research Track Unified Software Engineering agent as AI Software Engineer 16:45 - 17:00			ICSE Research Track Argus: A Multi-agent Sensitive Information Leakage Detection Framework ... 17:00 - 17:15			ICSE Research Track MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming 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
Asia I	ICSE Journal-first Papers Is Hyper-Parameter Optimization Different for Software Analytics? 11:00 - 11:15			ICSE Journal-first Papers On the Effectiveness of LLM-as-a-judge for Code Generation and Summariz ... 11:15 - 11:30			ICSE Journal-first Papers A Catalog of Data Smells for Coding Tasks 11:30 - 11:45			ICSE Journal-first Papers Towards Automating Domain-Specific Data Generation for Text-to-SQL: A C ... 11:45 - 12:00			ICSE New Ideas and Emerging Results (NIER) Empirical and Sustainability Aspects of Software Engineering Research i ... 12:00 - 12:15			ICSE Research Track FORGE: An LLM-driven Framework for Large-Scale Smart Contract Vulnerabi ... 12:15 - 12:30																					ICSE Demonstrations CI-Bench: A Framework for Evaluating Large Language Model Tools on CI F ... 14:00 - 14:15			ICSE Journal-first Papers Assessing the Latent Automated Program Repair Capabilities of Large Lan ... 14:15 - 14:30			ICSE Research Track XRFix: Exploring Performance Bug Repair of Extended Reality Application ... 14:30 - 14:45			ICSE Research TrackAward Winner Synthetic Repo-level Bug Dataset for Training Automated Program Repair ... 14:45 - 15:00			ICSE Research Track PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates 15:00 - 15:15			ICSE Research Track Input Reduction Enhanced LLM-based Program Repair 15:15 - 15:30									ICSE Research Track AdapTrack: Constrained Decoding without Distorting LLM's Output Intent 16:00 - 16:15			ICSE Research TrackAward Winner Evaluating Generated Commit Messages with Large Language Models 16:15 - 16:30			ICSE Research TrackAward Winner Automating Just-In-Time Python Type Annotation Updating 16:30 - 16:45			ICSE New Ideas and Emerging Results (NIER) Unveiling the Potential of Diffusion Large Language Models in Software ... 16:45 - 17:00			ICSE Research Track Enhancing LLM Code Generation with Ensembles: A Similarity-Based Select ... 17:00 - 17:15			ICSE Demonstrations Code4MeV2: a Research-oriented Code-completion Platform 17:15 - 17:30

Room information: Asia I

This program is tentative and subject to 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

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

Research Track + SE In Practice (SEIP)

Research Track + SE In Practice (SEIP)

SE In Practice (SEIP)

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

Research Track + Journal-first Papers

SE In Practice (SEIP) + Research Track

Research Track

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

New Ideas and Emerging Results (NIER) + Research Track + Journal-first Papers

Research Track + Demonstrations + Journal-first Papers

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

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

Tracks

Co-hosted Conferences

Workshops

Room information: Asia I

This program is tentative and subject to change.

Program Display Configuration

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

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

Research Track + SE In Practice (SEIP)

Research Track + SE In Practice (SEIP)

SE In Practice (SEIP)

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

Research Track + Journal-first Papers

SE In Practice (SEIP) + Research Track

Research Track

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

New Ideas and Emerging Results (NIER) + Research Track + Journal-first Papers

Research Track + Demonstrations + Journal-first Papers

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

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

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

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

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