by Mayank Patel | May 24, 2026 | 2026, Asim Unmesh, Karthik Ramani, Mayank Patel, Rahul Jain
Mechanical assembly animations are essential for conveying complex technical procedures, especially in instructional and training contexts. With the growing adoption of immersive Virtual Reality (iVR) in education and industry, there is a critical need for tools that...
by Xiyun Hu | Apr 13, 2026 | 2026, Chenfei Zhu, Dizhi Ma, Karthik Ramani, Rahul Jain, Shao-Kang Hsia, Xiyun Hu
Augmented Reality (AR) tutorials enhance procedural task learning by providing situated, step-by-step guidance. Yet, creating such tutorials requires AR authoring expertise, posing a significant entry barrier. To lower this barrier, we introduce ARify, an authoring...
by Runlin Duan | Apr 13, 2026 | 2026, Chenfei Zhu, Dizhi Ma, Karthik Ramani, Runlin Duan, Xiyun Hu, Yuzhao Chen, Ziyi Liu
Parametric modeling is a prevailing 3D modeling approach in design, architecture, and engineering. The emergence of multimodal large language models (LLMs) brings a new opportunity to lower the entry barriers to this powerful tool. However, describing 3D geometries...
by Ziyi Liu | Apr 13, 2026 | 2026, Karthik Ramani, Runlin Duan, Xiyun Hu, Yuzhao Chen, Zhengzhe Zhu, Ziyi Liu
Real-time handwriting interactions between tutors and students —where tutors observe individual problem-solving processes, provide personalized annotations, and adapt explanations based on students’ work—are fundamental to effective STEM tutoring. However, scaling...
by Dizhi Ma | Apr 13, 2026 | 2026, Dizhi Ma, Karthik Ramani, Xiyun Hu
We present AgentCoach, an LLM-powered system that provides adaptive feedback for motor skill learning from tutorial videos. The system works by extracting key coaching points (CPs) and compiling CP-specific evaluators that map each cue to measurable kinematic...
by Yuzhao Chen | Mar 23, 2026 | 2026, Chenfei Zhu, Jingyu Shi, Karthik Ramani, Rahul Jain, Runlin Duan, Yuzhao Chen
Generative AI (GenAI) has significantly advanced the ease and flexibility of image creation. However, it remains a challenge to precisely control spatial compositions, including object arrangement and scene conditions. To bridge this gap, we propose Canvas3D, an...
