Publications

Journal articles

• Abhinav Reddy Mandli, Saurabhsingh Rajput, Tushar Sharma. "COMET: Generating Commit Messages using Delta Graph Context Representation". Accepted in Journal of Systems and Software (JSS), Dec 2024. Preprint
• José Antonio Hernández López, Boqi Chen, Mootez Saad, Tushar Sharma, Dániel Varró. "On Inter-dataset Code Duplication and Data Leakage in Large Language Models". Accepted in Transactions of Software Engineering (TSE), Nov 2024. Preprint
• Saurabhsingh Rajput, Tim Widmayer, Ziyuan Shang, Maria Kechagia, Federica Sarro, Tushar Sharma. "Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement". Accepted in ACM Transactions on Software Engineering and Methodology (TOSEM), June 2024. Preprint
• Tushar Sharma, Maria Kechagia, Stefanos Georgiou, Rohit Tiwari, Indira Vats, Hadi Moazen, and Federica Sarro. "A Survey on Machine Learning Techniques Applied to Source Code". Accepted in Journal of Systems and Software, Dec 2023. Preprint
• Tushar Sharma, Stefanos Georgiou, Maria Kechagia, Taher A. Ghaleb, and Federica Sarro. "Investigating Developers' Perception on Software Testability and its Effects". Accepted in Empirical Software Engineering Journal, Jul 2023. Preprint
• Chaima Abid, Dhia Elhaq Rzig, Thiago Ferreira, Marouane Kessentini, Tushar Sharma. "X-SBR: On the Use of the History of Refactorings for Explainable Search-Based Refactoring and Intelligent Change Operators", Aug 2021, Transactions on Software Engineering (TSE), doi: 10.1109/TSE.2021.3105037.
• Tushar Sharma, Vasiliki Efstathiou, Panos Louridas, Diomidis Spinellis, "Code Smell Detection by Deep Learning and Transfer Learning", Mar 2021, Volume 176, 2021, 110936, ISSN 0164-1212, doi: 10.1016/j.jss.2021.110936. Preprint

Conference articles

• Indranil Palit, Tushar Sharma. "Reinforcement~Learning vs Supervised~Learning: A tug of war to generate refactored code accurately". Accepted in EASE (Research track) 2025.
• Tajmilur Rahman, Mengzhe Fei, Tushar Sharma, Chanchal Roy. "TS-Detector : Detecting Feature Toggle Usage Patterns". Accepted in FSE 2025 (Tools track).
• Mootez Saad, José Antonio Hernández López, Boqi Chen, Dániel Varró, and Tushar Sharma. "An adaptive language-agnostic pruning method for greener language models for code". Accepted in Foundations of Software Engineering (FSE 2025 - Research track). Preprint
• Ghazal Sobhani, Israat Haque, and Tushar Sharma. "It Works (only) on My Machine: A Study on Reproducibility Smells in Ansible Scripts". Accepted in Mining Software Repositories (MSR 2025 - Research track). Preprint
• Aryan Boloori, and Tushar Sharma. "DPy: Code Smells Detection Tool for Python". Accepted in Mining Software Repositories (MSR 2025 - Tools and dataset track). Preprint
• Henrique Nunes, Tushar Sharma, and Eduardo Figueiredo. "MaRV: A Manually Validated Refactoring Dataset". Accepted in ACM international conference on AI Foundation Models and Software Engineering (FORGE 2025) (Forge '25 Benchmarking).
• Sanidhya Vijayvargiya, Mootez Saad, and Tushar Sharma. "Enhancing Identifier Naming Through Multi-Mask Fine-tuning of Language Models of Code". Accepted in IEEE SCAM 2024, Aug 2024. Preprint
• Diomidis Spinellis, Panos Louridas, Maria Kechagia, Tushar Sharma. "Broken Windows: Exploring the Applicability of a Controversial Theory on Code Quality". Accepted in International Conference on Software Maintenance and Evolution ( ICSME ‘24), June 2024. Preprint
• Tajmilur Rahman, Imran Shalabi, Tushar Sharma. Exploring Influence of Feature Toggles on Code Complexity. EASE 2024. Preprint
• Tushar Sharma. Multi-faceted Code Smell Detection at Scale using DesigniteJava 2.0. MSR (Data/Tools track) 2024. Preprint
• Saurabh Singh Rajput, Maria Kechagia, Federica Sarro, and Tushar Sharma. Greenlight: Highlighting TensorFlow APIs Energy Footprint. MSR (Data/Tools track) 2024. Preprint
• Mootez Saad and Tushar Sharma. Naturalness of Attention: Revisiting Attention in Code Language Models, Accepted in ICSE (NIER) 2024, Nov 2023. Preprint
• Himesh Nandani, Mootez Saad and Tushar Sharma. Calibrating Deep Learning-based Code Smell Detection using Human Feedback, Accepted in IEEE SCAM, Aug 2023. Preprint
• Harsh Mukeshkumar Shah, Qurram Zaheer Syed, Bharatwaaj Shankaranarayanan, Indranil Palit, Arshdeep Singh, Kavya Raval, Kishan Savaliya and Tushar Sharma. Mining and Fusing Productivity Metrics with Code Quality Information at Scale, Accepted in IEEE ICSME (Tools track), Aug 2023. Preprint
• Indranil Palit, Gautam Shetty, Hera Arif and Tushar Sharma. Automatic Refactoring Candidate Identification Leveraging Effective Code Representation, Accepted in IEEE ICSME (NIER track), Aug 2023. Preprint
• Himesh Nandani, Mootez Saad, Tushar Sharma. DACOS-A Manually Annotated Dataset of Code Smells. Mining Software Repositories (MSR 2023) - Dataset and tools track. Preprint
• Stefanos Georgiou, Maria Kechagia, Tushar Sharma, Federica Sarro, Ying Zou. Green AI: Do Deep Learning Frameworks Have Different Costs? in 44th International Conference on Software Engineering (ICSE 2022) - Technical track. Preprint
• Akond Rahman, Tushar Sharma. Lessons from Research to Practice on Writing Better Quality Puppet Scripts. in 29th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2022. Pre-print
• Akash Rajesh Agrawal, Sung Jun Won, Mayuri Deshpande, Tushar Sharma, Christopher Carson McComb, "A Multi-Agent Reinforcement Learning Framework for Intelligent Manufacturing with Autonomous Mobile Robots", Apr 21, ICED21 23rd International Conference on Engineering Design.
• Alexandra-Maria Chaniotaki, Tushar Sharma "Architecture Smells and Pareto Principle: A Preliminary Empirical Exploration", MSR 2021 (Research track). Preprint
• Tushar Sharma, Marouane Kessentini. "QScored: A Large Dataset of Code Smells and Quality Metrics", MSR 2021 (Data showcase track). Preprint

Tutorials and technical briefings

• Tushar Sharma. "LLMs for code: the potential, prospects, and problems", International Conference on Software Architecture (ICSA) 2024.

Workshop papers

• Saurabh Singh Rajput and Tushar Sharma. "Pursuit of Energy-efficient AI: Benchmarking Emerging Neural Network Quantization Methods", 8th International Workshop on Green and Sustainable Software (GREENS 2024).

Technical reports

• Tushar Sharma, Maria Kechagia, Stefanos Georgiou, Rohit Tiwari, Indira Vats, Hadi Moazen, Federica Sarro. "A Survey on Machine Learning Techniques for Source Code Analysis", Oct 2021. Available on Arxiv.