Tony Haoran Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tony Haoran Feng has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Burkhard Claus Wuensche
University of Auckland, Auckland, New Zealand
11 shared publications - Andrew Luxton-Reilly
University of Auckland, Auckland, New Zealand
8 shared publications - Paul Denny
University of Auckland, Auckland, New Zealand
8 shared publications - Steffan Hooper
University of Auckland, Auckland, New Zealand
7 shared publications - Zixuan Wang
University of Auckland, Auckland, New Zealand
3 shared publications - Dominik Lange-Nawka
University of Auckland, Auckland, New Zealand
2 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Design and Evaluation of a Publication-focused Research-informed Advanced Computer Graphics Course
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessDesign and Evaluation of a Publication-focused Research-informed Advanced Computer Graphics Course
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
SketchBot: Towards a VLM-Based Formative Feedback Tool for Ray-Tracing Sketches in Computer Graphics Education
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessSketchBot: Towards a VLM-Based Formative Feedback Tool for Ray-Tracing Sketches in Computer Graphics Education
- 2 April 2026
- Published by Elsevier in Computers & Graphics
- Vol. 136
Comparative evaluation of LLMs in generating ray tracing programming exercise questions and solutions
- 2 April 2026
- Published by Elsevier in Computers & Graphics
- Vol. 136
Comparative evaluation of LLMs in generating ray tracing programming exercise questions and solutions
- Open Access
- 24 February 2026
- Published by Elsevier in SSRN Electronic Journal
Comparative Evaluation of LLMs in Generating Ray Tracing Exercise Questions
Ray Tracing is a fundamental concept often taught in introductory Computer Graphics courses. Ray-Object Intersection (ROI) questions are frequently used as practice for students, as they leverage various skills essential to learning Ray Tracing or Computer Graphics (CG) in general, such as geometry and spatial reasoning. Although these questions are useful in teaching practices, they may require significant time and effort to produce, as the production process can be quite complex and necessitates careful verification and review. Recent advancements in Generative Artificial Intelligence have led to the possibility of automated or assisted exercise generation, but this is underexplored in CG. To investigate this, we conducted experiments over two years and across three different models (GPT-4, o4-mini, and GPT-5.1) to evaluate the performance of LLMs in writing ROI programming questions and model solutions. The results indicate that there has been a significant performance improvement when writing ROI programming questions and model solutions with the newer models (o4-mini and GPT-5.1) over GPT-4. In particular, the newer models have achieved near-perfect scores with writing model solutions and are capable of generating teaching materials with strong baseline qualities that can be refined into high-quality resources through expert review. This demonstrates that LLMs can be proficient in this field, which can be leveraged to enhance the productivity of CG educators and provide CG students with more learning resources.
- 24 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessComparative Evaluation of LLMs in Generating Ray Tracing Exercise Questions
Ray Tracing is a fundamental concept often taught in introductory Computer Graphics courses. Ray-Object Intersection (ROI) questions are frequently used as practice for students, as they leverage various skills essential to learning Ray Tracing or Computer Graphics (CG) in general, such as geometry and spatial reasoning. Although these questions are useful in teaching practices, they may require significant time and effort to produce, as the production process can be quite complex and necessitates careful verification and review. Recent advancements in Generative Artificial Intelligence have led to the possibility of automated or assisted exercise generation, but this is underexplored in CG. To investigate this, we conducted experiments over two years and across three different models (GPT-4, o4-mini, and GPT-5.1) to evaluate the performance of LLMs in writing ROI programming questions and model solutions. The results indicate that there has been a significant performance improvement when writing ROI programming questions and model solutions with the newer models (o4-mini and GPT-5.1) over GPT-4. In particular, the newer models have achieved near-perfect scores with writing model solutions and are capable of generating teaching materials with strong baseline qualities that can be refined into high-quality resources through expert review. This demonstrates that LLMs can be proficient in this field, which can be leveraged to enhance the productivity of CG educators and provide CG students with more learning resources.
- Open Access
- 9 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 63-72
Bot or Prof: Comparing the Characteristics of AI-generated and Instructor-written Responses to Student Queries in an Introductory Programming Course Forum
- 9 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 63-72
Open AccessBot or Prof: Comparing the Characteristics of AI-generated and Instructor-written Responses to Student Queries in an Introductory Programming Course Forum
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Exploring Student Difficulties in Ray Tracing through Drawing-Based Tasks
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessExploring Student Difficulties in Ray Tracing through Drawing-Based Tasks
- Open Access
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1663-1664
Characteristics and Effectiveness of Cheat Sheets for a Third-year Computer Graphics and Image Processing Course
Student-created cheat sheets have been used to reduce exam anxiety, de-emphasize memorization, and enable students to focus on high-level learning. Previous work has identified cheat sheet properties which correlate with exam performance and has shown conflicting results about the benefits of cheat sheets for different subjects. However, no such study has been conducted for more advanced courses requiring knowledge from different fields and different representations, such as text, code, formulas, and images. We investigate which characteristics of student cheat sheets predict exam performance for a third-year Computer Graphics and Image Processing course. Our results show that higher exam scores are correlated with a better coverage of course material and more formulas, but not with having more images/diagrams, which were surprisingly uncommon. Having many example questions with sample solutions and missing lecture topics was correlated with lower grades. We hope to use our results to help students to better prepare for exams and create more effective cheat sheets.
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1663-1664
Open AccessCharacteristics and Effectiveness of Cheat Sheets for a Third-year Computer Graphics and Image Processing Course
Student-created cheat sheets have been used to reduce exam anxiety, de-emphasize memorization, and enable students to focus on high-level learning. Previous work has identified cheat sheet properties which correlate with exam performance and has shown conflicting results about the benefits of cheat sheets for different subjects. However, no such study has been conducted for more advanced courses requiring knowledge from different fields and different representations, such as text, code, formulas, and images. We investigate which characteristics of student cheat sheets predict exam performance for a third-year Computer Graphics and Image Processing course. Our results show that higher exam scores are correlated with a better coverage of course material and more formulas, but not with having more images/diagrams, which were surprisingly uncommon. Having many example questions with sample solutions and missing lecture topics was correlated with lower grades. We hope to use our results to help students to better prepare for exams and create more effective cheat sheets.
- Top Cited PapersOpen Access
- 12 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 164-171
From Automation to Cognition: Redefining the Roles of Educators and Generative AI in Computing Education
- 12 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 164-171
Top Cited PapersOpen AccessFrom Automation to Cognition: Redefining the Roles of Educators and Generative AI in Computing Education
- Open Access
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
An Eye for an AI: Evaluating GPT-4o's Visual Perception Skills and Geometric Reasoning Skills Using Computer Graphics Questions
- 22 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessAn Eye for an AI: Evaluating GPT-4o's Visual Perception Skills and Geometric Reasoning Skills Using Computer Graphics Questions
- Open Access
- 7 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 519-525
Advancing Automated Assessment Tools - Opportunities for Innovations in Upper-level Computing Courses: A Position Paper
- 7 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 519-525
Open AccessAdvancing Automated Assessment Tools - Opportunities for Innovations in Upper-level Computing Courses: A Position Paper