From the 1 of 10 linked papers with an AI index.
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
The paper empirically investigates why GPU kernels written in modern DSLs like Triton and TileLang can be functionally correct yet dramatically slower than library implementations,…
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…
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…
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…
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…