5 citations · 10 across the 8 of their papers we have counts for
10 papers
K2P: Label-Free Knowledge to Prompt Distillation
Yingchuan Zhang, Haoran Lu, Wenxuan Zhong +1
Knowledge distillation can transfer reasoning from stronger teachers to frozen students through reusable prompts, but avoiding weight updates does not eliminate supervision. Withou…
A Statistical Perspective on Knowledge Distillation: Foundations, Classical Methods, and Large Language Model Extensions
Luyang Fang, Haoran Lu, Jiazhang Cai +4
Knowledge Distillation (KD) has emerged as a vital paradigm for transferring the capabilities of high-capacity models to efficient ``student'' counterparts, addressing critical cha…
Knowledge Cascade: Reverse Knowledge Distillation on Nonparametric Multivariate Functional Estimation
Luyang Fang, Haoran Lu, Yongkai Chen +2
As machine learning models and datasets continue to grow, developing complex models has become increasingly computationally demanding. Knowledge distillation reduces deployment cos…
Confidence-Aware Automated Assessment of Student-Drawn Scientific Models
Luyang Fang, Yingchuan Zhang, Jongchan Park +3
Student-generated drawings are widely used in science education to assess learners' conceptual understanding in modeling-based tasks aligned with the Next Generation Science Standa…
Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
Luyang Fang, Yongkai Chen, Jiazhang Cai +2
Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. Ho…
NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
Haoran Lu, Luyang Fang, Wenxuan Zhong +1
Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose N…
Generalizable and Efficient Automated Scoring with a Knowledge-Distilled Multi-Task Mixture-of-Experts
Luyang Fang, Tao Wang, Ping Ma +1
Automated scoring of written constructed responses typically relies on separate models per task, straining computational resources, storage, and maintenance in real-world education…
Efficient Multi-Task Inferencing: Model Merging with Gromov-Wasserstein Feature Alignment
Luyang Fang, Ehsan Latif, Haoran Lu +3
Automatic scoring of student responses enhances efficiency in education, but deploying a separate neural network for each task increases storage demands, maintenance efforts, and r…
A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education
Ehsan Latif, Yifan Zhou, Shuchen Guo +24
As artificial intelligence (AI) continues to advance, it demonstrates capabilities comparable to human intelligence, with significant potential to transform education and workforce…
Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments
Ehsan Latif, Luyang Fang, Ping Ma +1
This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically…