< Back Coming up: iGGi Open Day! Coming Up: iGGi Open Day! To all prospective Applicants to iGGi: Don’t forget to register for our *in-person* Open Day (if you can make it) >> iGGi OPEN DAY << at University of York (Village East) and Queen Mary University of London (Whitechapel Campus) Tuesday 10 Jan 2023, 12:00-15:30 Come along to meet iGGi Researchers/Supervisors/Staff in person Schedule + REGISTRATION: >> for York here: https://tinyurl.com/yvwpp5bz >> for London here: https://tinyurl.com/bdcr3xfy We look forward to meeting you! *The photo is from our recent Game AI Group December Party!! at Empire House (QMUL Whitechapel Campus) Previous 20 Dec 2022 Next

< Back RESP: Reference-guided Sequential Prompting for Visual Glitch Detection in Video Games Link Author(s) Y Yu, A Wiens, A Barahona-Ríos, B Wilkins, S Zadtootaghaj, N Barman, ... Abstract More info TBA Link

< Back iGGi Talk at Develop:Brighton - Dominik Jeurissen iGGi PG Researcher Dominik Jeurissen held a talk on " LLM Agents For QA - Potential & Limitations " at this year's Develop:Brighton conference. Abstract: With tight deadlines and a constantly evolving game, properly testing a game is challenging. Using AI agents to simplify this work sounds promising, but machine learning is often too slow, and manually implementing the agents takes time. As such, one particularly exciting application for QA is to use Large Language Models (LLMs) as zero-shot game-playing agents. LLM-based agents can play games without pre-training, making them a valuable asset to test a constantly changing game. But how well do they play games? What are their strengths, and what do they struggle with? In this session, we will review how to implement zero-shot agents with LLMs and show examples of existing LLM-based game-playing agents. We will also show that although these agents have many limitations, they have the potential to be a valuable tool for QA to automate many repetitive tasks. The objectives of Dominik's talk were to provide the audience with an overview of the cutting-edge research on LLM-based zero-shot game-playing agents show what these agents can do well and what their limitations are give practical tips on how to utilize LLM agents as QA tools Dominik's talk has been recorded and will be made available to Develop ticket holders. Please contact Dominik directly if you have any queries regarding the presentation. Previous 11 Jul 2024 Next

< Back Metagame Autobalancing for Competitive Multiplayer Games Link Author(s) D Hernandez, CTT Gbadamosi, J Goodman, JA Walker Abstract More info TBA Link

< Back A Vocabulary of Board Game Dynamics Link Author(s) J Kritz, G Xexéo Abstract More info TBA Link

< Back AutoGraff: Towards a computational understanding of graffiti writing and related art forms Link Author(s) D Berio Abstract More info TBA Link

< Back Not All the Same: Understanding and Informing Similarity Estimation in Tile-Based Video Games Link Author(s) S Berns, V Volz, L Tokarchuk, S Snodgrass, C Guckelsberger Abstract More info TBA Link

< Back Redundancy Resolution in Trimanual vs. Bimanual Tracking Tasks Link Author(s) A Sanmartín-Senent, N Peña-Perez, E Burdet, J Eden Abstract More info TBA Link

< Back Examining the effects of video game difficulty adaptation on performance and player experience Link Author(s) M Frister, P Cairns, F McNab Abstract More info TBA Link

< Back How do loot boxes make money? An analysis of a very large dataset of real Chinese CSGO loot box openings Link Author(s) D Zendle, E Petrovskaya, H Wardle Abstract More info TBA Link

< Back HarmonyMapper: Generating Emotionally Divers Chord Progressions for Games. Link Author(s) S Cardinale, O Withington Abstract More info TBA Link

< Back Transforming the output of GANs by fine-tuning them with features from different datasets Link Author(s) T Broad, M Grierson Abstract More info TBA Link