128 citations · 262 across the 31 of their papers we have counts for
9 papers · 1 filter
Train4Merge: RL or SFT---Which Yields Better Teachers for OPD-Based Model Merging?
Jingyuan Huang, Zuming Huang, Yucheng Shi +4
Domain experts trained from a shared checkpoint can transfer their specialized capabilities to a single student through on-policy distillation (OPD). Existing research primarily fo…
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…
Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding
Jingyuan Huang, Zuming Huang, Yucheng Shi +4
GUI grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordinates. On-policy self-distill…
Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
Qitao Tan, Xiaoying Song, Arman Akbari +7
Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models m…
Fine-tuning ChatGPT for Automatic Scoring of Written Scientific Explanations in Chinese
Jie Yang, Ehsan Latif, Yuze He +1
The development of explanations for scientific phenomena is essential in science assessment, but scoring student-written explanations remains challenging and resource-intensive. La…
Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Education
Arne Bewersdorff, Christian Hartmann, Marie Hornberger +6
The integration of Artificial Intelligence (AI), particularly Large Language Model (LLM)-based systems, in education has shown promise in enhancing teaching and learning experience…
Gemini Pro Defeated by GPT-4V: Evidence from Education
Gyeong-Geon Lee, Ehsan Latif, Lehong Shi +1
This study compared the classification performance of Gemini Pro and GPT-4V in educational settings. Employing visual question answering (VQA) techniques, the study examined both m…
NERIF: GPT-4V for Automatic Scoring of Drawn Models
Gyeong-Geon Lee, Xiaoming Zhai
Scoring student-drawn models is time-consuming. Recently released GPT-4V provides a unique opportunity to advance scientific modeling practices by leveraging the powerful image pro…
Multimodality of AI for Education: Towards Artificial General Intelligence
Gyeong-Geon Lee, Lehong Shi, Ehsan Latif +10
This paper presents a comprehensive examination of how multimodal artificial intelligence (AI) approaches are paving the way towards the realization of Artificial General Intellige…