2 citations · 2 across the 11 of their papers we have counts for
13 papers
Beyond Confidence: Rethinking Uncertainty Calibration in Deep Code Models
Ravishka Rathnasuriya, Wei Yang
Deep learning models have shown significant promise in code-related tasks. While confidence calibration techniques have been proposed to improve model reliability, their effectiven…
RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation
Zixuan Yang, Yiqun Chen, Qi Liu +6
Open-ended generation lacks canonical answers, making pointwise rewards difficult to calibrate for group-based reinforcement learning. Directly ranking same-query rollouts provides…
WatchPoint: Executable User Feedback for Real-World Agentic Web Development
Guanqun Yang, Wei Yang, Xueqing Liu
When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click buttons, inspect computed styles, a…
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…
UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
Yiqun Chen, Wei Yang, Erhan Zhang +14
LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely op…
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…
Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
Zixuan Yang, Yiqun Chen, Wei Yang +7
Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based metho…
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…
Efficiency Robustness of Dynamic Deep Learning Systems
Ravishka Rathnasuriya, Tingxi Li, Zexin Xu +4
Deep Learning Systems (DLSs) are increasingly deployed in real-time applications, including those in resourceconstrained environments such as mobile and IoT devices. To address eff…
Can You Mimic Me? Exploring the Use of Android Record & Replay Tools in Debugging
Zihe Song, S M Hasan Mansur, Ravishka Rathnasuriya +4
Android User Interface (UI) testing is a critical research area due to the ubiquity of apps and the challenges faced by developers. Record and replay (R&R) tools facilitate manual…
CodeImprove: Program Adaptation for Deep Code Models
Ravishka Rathnasuriya, Zijie Zhao, Wei Yang
Leveraging deep learning (DL)-based code analysis tools to solve software engineering tasks is becoming increasingly popular. Code models often suffer performance degradation due t…