2 citations · 4 across the 5 of their papers we have counts for
6 papers
SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops
Ranran Haoran Zhang, Aysa Xuemo Fan, David Munhá Correia +2
Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which eval…
Toward Measuring AI's Effects on Skill Formation: The Stock-Formation Gap
Aysa Xuemo Fan
Large-scale AI deployment data and controlled learning experiments characterize different consequences of the same technology. Deployment telemetry shows that AI use is concentrate…
Evaluating the Quality of Code Comments Generated by Large Language Models for Novice Programmers
Aysa Xuemo Fan, Arun Balajiee Lekshmi Narayanan, Mohammad Hassany +1
Large Language Models (LLMs) show promise in generating code comments for novice programmers, but their educational effectiveness remains under-evaluated. This study assesses the i…
Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses
Aysa Xuemo Fan, Ranran Haoran Zhang, Luc Paquette +1
In this paper, we explore the application of large language models (LLMs) for generating code-tracing questions in introductory programming courses. We designed targeted prompts fo…
ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining
Ranran Haoran Zhang, Aysa Xuemo Fan, Rui Zhang
A universal classification model aims to generalize to diverse classification tasks in both zero and few shot settings. A promising way toward universal classification is to cast h…
Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan +5
Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence gen…