Mury Fajar Dewantoro

Mr. Mury Fajar Dewantoro


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2023
Verified
Book Chapter
Closed access
PDF file
Mustafa Can GursesliMustafa Can Gursesli
Mustafa Can Gursesli
PTPittawat Taveekitworachai
Pittawat Taveekitworachai
FAFebri Abdullah
Febri Abdullah
MDMury Fajar Dewantoro
Mury Fajar Dewantoro
Antonio LanatàAntonio Lanatà
Antonio Lanatà
RTRuck Thawonmas
Ruck Thawonmas

31 October 2023
Verified
Book Chapter
Closed access
PDF file
PTPittawat Taveekitworachai
Pittawat Taveekitworachai
FAFebri Abdullah
Febri Abdullah
Mustafa Can GursesliMustafa Can Gursesli
Mustafa Can Gursesli
MDMury Fajar Dewantoro
Mury Fajar Dewantoro
SCSiyuan Chen
Siyuan Chen
RTRuck Thawonmas
Ruck Thawonmas

12 March 2024 in IEEE Transactions on Games
Verified
Journal Article
Closed access
FAFebri Abdullah
Febri Abdullah
PTPittawat Taveekitworachai
Pittawat Taveekitworachai
MDMury Fajar Dewantoro
Mury Fajar Dewantoro
RTRuck Thawonmas
Ruck Thawonmas
JTJulian Togelius
Julian Togelius
JRJochen Renz
Jochen Renz
This study summarizes the first ChatGPT4PCG competition held at the 2023 IEEE Conference on Games. The goal of the competition is to explore emergent abilities of publicly available LLMs in performing complex tasks related to procedural content generation, specifically physics-based level generation for Angry Bird-like games. Participants are tasked with submitting their prompts for ChatGPT to generate Angry Birds-like game structures that resemble English uppercase characters. A structure is a collection of stacked game objects comprising a part of an entire Angry Birds-like level. A prompt is an input for large language models (LLMs) including ChatGPT. Two evaluation metrics, i.e., stability and similarity, are used to evaluate the submitted prompts. Stability measures the sturdiness of a structure to withstand in-game gravity, while similarity measures a structure's resemblance to the target character. With such evaluation, participants are challenged not only to produce character-like but also stable structures by utilizing prompt engineering techniques. Finally, the competition's results are discussed to provide valuable insights for future studies and competitions.

31 October 2023
Verified
Book Chapter
Closed access
PDF file
PTPittawat Taveekitworachai
Pittawat Taveekitworachai
FAFebri Abdullah
Febri Abdullah
Mustafa Can GursesliMustafa Can Gursesli
Mustafa Can Gursesli
MDMury Fajar Dewantoro
Mury Fajar Dewantoro
SCSiyuan Chen
Siyuan Chen
RTRuck Thawonmas
Ruck Thawonmas

22 July 2025 in International Journal of Human–Computer Interaction
Verified
Journal Article
Open access
Mustafa Can GursesliMustafa Can Gursesli
Mustafa Can Gursesli
SCSiyuan Chen
Siyuan Chen
MDMury Fajar Dewantoro
Mury Fajar Dewantoro
XYXiao You
Xiao You
EAEge Anbar
Ege Anbar
RTRuck Thawonmas
Ruck Thawonmas

14 January 2025 in IEEE Transactions on Games
Verified
Journal Article
Closed access
PTPittawat Taveekitworachai
Pittawat Taveekitworachai
MDMury Fajar Dewantoro
Mury Fajar Dewantoro
YXYi Xia
Yi Xia
PSPratch Suntichaikul
Pratch Suntichaikul
RTRuck Thawonmas
Ruck Thawonmas
This paper presents BenchING, a new benchmark for evaluating large language models (LLMs) on their ability to follow structured output format instructions in text-based procedural content generation (PCG) tasks. The ability to condition LLMs to output in specified formats proves useful, as downstream components in LLM-integrated games often require structured outputs for exchanging information. However, there is a gap in evaluating this aspect of LLMs, especially in narrative PCG tasks, making it difficult to select LLMs and design games or applications integrating these LLMs. To demonstrate the potential of our benchmark, we evaluate nine LLMs for their ability to generate parseable formatted outputs using five selected text-based PCG tasks. We report on the performance of these LLMs on these tasks. Additionally, we categorize more detailed error types and propose solutions by utilizing LLMs to fix these errors. We also conduct a scaling study, investigating an emergent point of LLMs for their ability to fix malformed formatted content using eight quantized LLMs with varying original sizes from 0.62B to 72.3B. Furthermore, we perform a qualitative study to assess the quality of the generated content. We make our source code and raw data available for future research.