*indicating first authored publications

1.  Ravishka Rathnasuriya*, Zihe Song, Wei Yang. An Investigation on Numerical Bugs in GPU Programs Towards Automated Bug Detection. ACM SIGSOFT 34th International Symposium on Software Testing and Analysis (ISSTA 2025), 2025.

2. Ravishka Rathnasuriya*, Zijie Zhao, Wei Yang. CodeImprove: Program Adaptation for Deep Code Models. In The 47th International Conference on Software Engineering (ICSE 2025), 2025. Paper 

3. Ravishka Rathnasuriya*. A Framework for On the Fly Input Refinement for Deep Learning Models. Doctoral Symposium in the 47th International Conference on Software Engineering (ICSE-DS 2025), 2025.

4. Ravishka Rathnasuriya*. On the Fly Input Refinement for Code Language Models. Student Research Competition in the 47th International Conference on Software Engineering (ICSE-SRC 2025), 2025.

5. Zihe Song, S M Hasan Mansur, Ravishka Rathnasuriya, Yumna Fatima, Wei Yang, Kevin Moran, Wing Lam. Can you mimic me? Exploring the Use of Android Record & Replay Tools in Debugging. In The 12th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2025), 2025.

6. Jiangrui Zheng, Xueqing Liu, Guanqun Yang, Mirazul Haque, Xing Qian, Ravishka Rathnasuriya, Girish Budhrani, Wei Yang. HateModerate: Testing Hate Speech Detectors against Content Moderation Policies. In the Annual Conference of the North American Chapter of the Association for Computational Linguistics -Findings. (NAACL 2024).

*indicating first authored submissions

1. Ravishka Rathnasuriya*, Mirazul Haque, Tingxi Li, Zexin Xu, Simin Chen, Zihe Song, Wei Yang. SoK: A Taxonomy of Efficiency Attacks in Dynamic Deep Learning Systems.

2. Ravishka Rathnasuriya*, Wei Yang. Beyond Confidence: Rethinking Uncertainty Calibration in Deep Code Models.

3. Ravishka Rathnasuriya*, Wei Yang. Towards Foundation Models for Users with Customized Requirements: Bridging the Gap Between General Models and Specific Needs.  

4. Ravishka Rathnasuriya*, Simin Chen, Wei Yang. An Empirical Study on Automated Oracle Generation for Testing Deep Learning Application.

I am leading the following projects currently. 

1. Input Validation for DL/LLMs on Software Engineering-, Natural Language-, and Computer Vision- based tasks.

2. Input Refinement for DL/LLMs on Software Engineering-, Natural Language-, and Computer Vision- based tasks at deployment stage.

3. Selecting Effective Code Generations via Black Box Approach on Code LLMs.

4. Efficiency Robustness on Dynamic Deep Learning Systems (Mixture-of-Experts, Mixture-of-Depths, and Sparsity).

5. Program analysis on numerical bugs detection for GPU programs, differential/metamorphic testing for DL models.