Minghua Ma

AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models

2024 · arXiv (Cornell University)

Verbatim feedback constitutes a valuable repository of user experiences, opinions, and requirements essential for software development. Effectively and efficiently extracting valuable insights from such data poses a challenging task. This paper introduces Allhands , an …

Semantic Scheduling for LLM Inference

2025 · arXiv (Cornell University)

Conventional operating system scheduling algorithms are largely content-ignorant, making decisions based on factors such as latency or fairness without considering the actual intents or semantics of processes. Consequently, these algorithms often do not prioritize tasks …