2 citations · 2 across the 10 of their papers we have counts for
10 papers
Correct but Slow: An Empirical Study of the GPU Kernel Evaluation Gap in Modern Domain-Specific Languages
Tingxi Li, Ravishka Rathnasuriya, Wei Yang
Modern GPU domain-specific languages (DSLs), such as Triton and TileLang, are increasingly used to implement specialized deep-learning kernels and as target languages for automated…
When to Answer and When to Defer: A Decision Framework for Reliable Code Predictions
Ravishka Rathnasuriya, Wei Yang
Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect prediction…
On-the-Fly Input Adaptation for Reliable Code Intelligence
Ravishka Rathnasuriya, Wei Yang
Code language models (CLMs) play a central role in software engineering across both generation and classification tasks. However, these models still exhibit notable mispredictions…
AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines
Tingxi Li, Mingfang Ji, Ravishka Shemal Rathnasuriya +3
Modern machine learning deployments increasingly compose specialized models into dynamic inference pipelines, where upstream components produce intermediate predictions that determ…
Characterizing Real-World Bugs in Tile Programs for Automated Bug Detection
Ravishka Rathnasuriya, Zihe Song, Nidhi Majoju +4
Tile-based programming frameworks are increasingly adopted to write high-performance GPU kernels in domains such as deep learning and scientific computing. While these frameworks e…
Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems
Ravishka Rathnasuriya, Wei Yang
The growing deployment of deep learning models in real-world environments has intensified the need for efficient inference under strict latency and resource constraints. To meet th…