Search Results

< Back James Gardner University of York iGGi PG Researcher I am a third-year PhD student at The University of York, specialising in computer vision and machine learning for 3D scene understanding. Supervised by Dr William Smith, my research focuses on neural-based vision and language priors in inverse rendering and scene representation learning. I'm particularly interested in neural fields, generative models, 3D computer vision, differentiable rendering, geometric deep learning, multi-modal models, and 3D scene understanding in general. My research has been recognised with publications at prestigious conferences including NeurIPS and ECCV. Currently, I am working as a research fellow on the ALL.VP project, funded by BridgeAI and Dock10, developing relightable green screen performance capture using deep learning and inverse rendering techniques. This work aims to provide greater creative control to film and TV productions without requiring expensive LED volumes or post-production. I hold an MEng in Electronic Engineering from The University of York, for which I was awarded the IET Prize for outstanding performance and the Malden Owen Award for the best-graduating student on an MEng programme. A description of James' research: My research lies at the intersection of computer vision, machine learning, and 3D scene understanding, with a particular focus on neural-based approaches and the integration of vision and language priors. My work spans a range of topics including neural fields, generative models, differentiable rendering, and geometric deep learning. A key theme in my research is the use of 3D inductive biases for inverse rendering, addressing challenges such as illumination estimation, albedo/geometry disentanglement, and shadow handling in complex outdoor scenes. I've made contributions in creating a rotation-equivariant neural illumination model and spherical neural models for sky visibility estimation in outdoor inverse rendering. Additionally, my work extends to learning rotation-equivariant latent representations of the world from 360-degree videos, aimed at advancing the field of 3D scene understanding and developing models with an understanding of core physical principles such as object permanence. Through my research, I aim to build computer systems capable of deeply comprehending the 3D world, utilising self-supervised, generative, and non-generative approaches to push the boundaries of what's possible in computer vision and scene representation learning. james.gardner@york.ac.uk Email Mastodon Other links Website https://www.linkedin.com/in/jadgardner/ LinkedIn BlueSky https://jadgardner.github.io/ Github Featured Publication(s): The Sky's the Limit: Relightable Outdoor Scenes via a Sky-Pixel Constrained Illumination Prior and Outside-In Visibility Themes Game AI - Previous Next

< Back Intelligent Games and Game Intelligence at Develop:Brighton 12-14 July Want to improve the relationship between your game AI and your players? Or polish your VR character’s social interaction skills? Or discuss the latest academic research in the metaverse? Or just chance a flirt with Amy Smith ’s @artbhot? We are super excited to announce that @iggiphd will be attending @developconf in full force with 3 talks and over 20 researchers. This is our first big event since the pandemic and we are stoked! Who else is coming? We would love to meet you all at our stand! Click here for more information. Previous 2 Jul 2022 Next

< Back Dr Daniel Berio Goldsmiths iGGi Alum AutoGraff: A Procedural Model of Graffiti Form. (Industry placement at Media Molecule) The purpose of this study is to investigate techniques for the procedural and interactive generation of synthetic instances of graffiti art. Considering graffiti as a special case of the calligraphic tradition, I propose a "movement centric" alternative to traditional curve generation techniques, in which a curve is defined through a physiologically plausible simulation of a (human) movement underlying its production rather than by an explicit definition of its geometry. In my thesis, I consider both single traces left by a brush (in a series of strokes) and the extension to 2D shapes (representing deformed letters in a large variety of artistic styles). I demonstrate how this approach is useful in a number of settings including computer aided design (CAD), procedural content generation for virtual environments in games and movies, computer animation as well as for the smooth control of robotic drawing devices. Daniel Berio is a researcher and artist from Florence, Italy. Since a young age Daniel was actively involved in the international graffiti art scene. In parallel he developed a professional career initially as a graphic designer and later as a graphics programmer in video games, multimedia and audio-visual software. In 2013 he obtained a Master degree from the Royal Academy of Art in The Hague (Netherlands), where he developed drawing machines and installations materializing graffiti-inspired procedural forms. Today Daniel is continuing his research in the procedural generation of graffiti within the IGGI (Intelligent Games and Game Intelligence) PhD program at Goldsmiths, University of London. Please note: Updating of profile text in progress Email Mastodon Other links Website LinkedIn BlueSky Github Featured Publication(s): Optimality Principles in the Procedural Generation of Graffiti Style SURFACE: Xbox Controlled Hot-wire Foam Cutter The role of image characteristics and embodiment in the evaluation of graffiti Emergence in the Expressive Machine The CyberAnthill: A Computational Sculpture Sketch-Based Modeling of Parametric Shapes Artistic Sketching for Expressive Coding Calligraphic stylisation learning with a physiologically plausible model of movement and recurrent neural networks Sequence generation with a physiologically plausible model of handwriting and Recurrent Mixture Density Networks AutoGraff: Towards a computational understanding of graffiti writing and related art forms Kinematics reconstruction of static calligraphic traces from curvilinear shape features Interactive generation of calligraphic trajectories from Gaussian mixtures Sketching and Layering Graffiti Primitives. Kinematic Reconstruction of Calligraphic Traces from Shape Features Expressive curve editing with the sigma lognormal model Dynamic graffiti stylisation with stochastic optimal control Computer aided design of handwriting trajectories with the kinematic theory of rapid human movements Generating calligraphic trajectories with model predictive control Learning dynamic graffiti strokes with a compliant robot Computational models for the analysis and synthesis of graffiti tag strokes Towards human-robot gesture recognition using point-based medialness Transhuman Expression Human-Machine Interaction as a Neutral Base for a New Artistic and Creative Practice Themes Game AI - Previous Next

< Back Tackling sparse rewards in real-time games with statistical forward planning methods Link Author(s) RD Gaina, SM Lucas, D Perez-Liebana Abstract More info TBA Link

< Back Michelangelo Conserva Queen Mary University of London iGGi PG Researcher Available for post-PhD position Michelangelo Conserva is a second year PhD researcher studying principled exploration strategies in reinforcement learning. He is particularly interested in randomized exploration and, more generally, Bayesian methods for reinforcement learning. He holds a BSc in Statistics, Economics and Finance from Sapienza, University of Rome and an MSc in Computational Statistics and Machine learning from University College of London. A description of Michelangelo's research: As a PhD student at Queen Mary University of London, Michelangelo aims to leverage Bayesian models to develop principled algorithms for reinforcement learning in the context of function approximations. The main challenge lies in finding a balance between computational costs and optimality. Evaluating such balance requires careful evaluation, which is currently lacking in reinforcement learning. m.conserva@qmul.ac.uk Email Mastodon https://michelangeloconserva.github.io/ Other links Website https://www.linkedin.com/in/michelangeloconserva/ LinkedIn BlueSky https://github.com/MichelangeloConserva Github Supervisors: Prof. Simon Lucas Dr Paulo Rauber Featured Publication(s): What are you looking at? Team fight prediction through player camera Posterior Sampling for Deep Reinforcement Learning Hardness in Markov Decision Processes: Theory and Practice Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual Bandits The Graph Cut Kernel for Ranked Data Themes Game AI - Previous Next

< Back Dominik Jeurissen Queen Mary University of London iGGi PG Researcher Hey, I'm Dominik Jeurissen, and I'm passionate about both software engineering and machine learning, with a particular interest in fully autonomous agents that do not rely on absurd amounts of data. My focus areas include reinforcement learning, unsupervised learning, and the emerging capabilities of large language models. I earned my MSc in Artificial Intelligence from Maastricht University and my BSc in Computer Science with a focus on Applied Mathematics from RWTH Aachen. During my undergraduate studies, I worked as a software engineer at INFORM GmbH, contributing to their supply management software, add*ONE. A description of Dominik's research: My PhD is a collaboration with Creative Assembly , focusing on researching AI for complex strategy games, such as Total War. With the recent emergence of Large Language Models (LLMs), I’m exploring their potential to enhance game-playing agents. LLMs can instantly recall knowledge on almost any topic (though not without occasional errors), perform basic reasoning, and are easily configured for a wide range of text-based tasks. These abilities make them especially promising for game development, where machine learning agents often struggle due to constantly changing game environments. d.jeurissen@qmul.ac.uk Email https://commandercero.github.io/ Mastodon Other links Website https://www.linkedin.com/in/dominik-jeurissen/ LinkedIn https://bsky.app/profile/dominikjeurissen.bsky.social BlueSky https://github.com/CommanderCero Github Supervisors: Dr Diego Pérez-Liébana Dr Jeremy Gow Featured Publication(s): Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games Generating Diverse and Competitive Play-Styles for Strategy Games PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games Automatic Goal Discovery in Subgoal Monte Carlo Tree Search Game state and action abstracting monte carlo tree search for general strategy game-playing Portfolio search and optimization for general strategy game-playing The Design Of" Stratega": A General Strategy Games Framework Themes Design & Development Game AI Game Data - Previous Next

News (All) iGGi is a collaboration between Uni of York + Queen Mary Uni of London: the largest training programme worldwide for doing a PhD in digital games. iGGi News 12 Sept 2025 iGGi Con 2025 Successfully Concluded! The world's favourite doctoral training programme has done it again! Its annual conference was held at York this week, and It's A Wrap! Read More 8 Jul 2025 Nirit Binyamini Ben-Meir wins Best Paper Award at DIS25 iGGi PGR wins Best Paper with their work on "Domestic Cultures of Plant Care: A Moss Terrarium Probe" Read More 7 May 2025 iGGi/AIM/C4DM Spring Writing Retreat 2025 Every year, iGGi runs at least one Writing Retreat to facilitate focused writing on research and projects away from home in a tranquil environment. Read on for this time's story.. Read More 21 Aug 2025 iGGi Research Retreat "Unconference" at Darwin Lake in Derbyshire.... Read More 3 Jun 2025 UK Games Expo Birmingham For the first time running, iGGi had its own stand at the UK Games Expo in Birmingham this year! Read More 2 Apr 2025 iGGi @ GDC 2025 Six iGGis flew to California this March to attend the GDC... Six iGGis, six Blogs. Read More 10 Jul 2025 iGGi @ Develop:Brighton 2025 iGGi PGR Francesca Foffano delivered a captivating talk at Develop 2025. AND, for the 4th year running, iGGi featured on the Develop Expo with its own stand. This may have been our most successful year to date!! Read More 7 May 2025 iGGi Con 2025 - REGISTRATION NOW OPEN! We're excited to share that registrations for the upcoming iGGi Conference are now open! This year's iGGi Con takes place at the University of York, 10-11 September 2025. Read on for links and more info. Read More 13 Jan 2025 iGGi Game Jam 2025 and Awards! iGGi successfully concluded its 11th Game Jam on Friday, and it’s been EPIC! Read More Load More

iGGi Unconference Group Outcomes (List) iGGi is a collaboration between Uni of York + Queen Mary Uni of London: the largest training programme worldwide for doing a PhD in digital games. iGGi Research Retreat "Unconference" Since Summer 2024, iGGi has been running a "Research Retreat" (aka "Unconference") at a secluded cottage village in Derbyshire. We gather 30 people made up of iGGi PGRs, Alumni, Staff and Industry Partners and ask: What are the nagging questions from your PhD research (or, for industry partners: in your work or from your pet project) where you could use new eyes and approaches? What are the most intriguing research questions in your area? What ideas has your research/work/hobby thrown up that you'd love to take a closer look at? What are the key research ideas and questions in other areas? The ideas to be explored emerge during the retreat: Everyone can propose an idea/topic/"problem", and participants then choose which small group they would like to join to explore further. To play with new ideas. Below you can find a selection of group outcomes from the 2025 iGGi Unconference iGGi Research Retreat "Unconference" August 2025 The Future of AI This group discussed what the "future of AI" might look like, how it will change us as a society and what possibilities it could create. Read More iGGi Research Retreat "Unconference" August 2025 Trust and Freedom in Transformative Games This group discussed how games build or break trust and the factors involved in creating tustworthy games. Read More iGGi Research Retreat "Unconference" August 2025 Generative AI, Abstraction and Epistemology This group tried to come up with the skeleton of a short presentation for technologists in the former CIS region about the topic. Read More iGGi Research Retreat "Unconference" August 2025 Social Simulation Game on a Graph / Network This group started off with the idea of a cellular automaton and set off to investigat how such a simple structure could be rendered as a playable simulation of social dynamics. Read More

Publications (All) iGGi is a collaboration between Uni of York + Queen Mary Uni of London: the largest training programme worldwide for doing a PhD in digital games. iGGi Publications Filter by iGGi Theme Accessibility Applied Games Creative Computing Design & Development Esports Game AI Game Audio Game Data Games Business Immersive Technology Player Research Filter by iGGi Author Select iGGi Author Filter by Publication Year Select year Filter by Publication Type Select Publication Type World and human action models towards gameplay ideation A Kanervisto, D Bignell, LY Wen, M Grayson, R Georgescu, ... Nature 638 (8051), 656-663, 2025 Marko Tot View Details Cost-Effective Attention Mechanisms for Low Resource Settings: Necessity & Sufficiency of Linear Transformations P Hosseini, M Hosseini, I Castro, M Purver arXiv preprint arXiv:2403.01643, 2025 Peyman Hosseini View Details Domestic Cultures of Plant Care: A Moss Terrarium Probe N. Binyamini Ben-Meir, P.G.T. Healey, S. Deterding Designing Interactive Systems Conference (DIS '25), 05-09 July 2025, Funchal, Portugal. ACM, New York, NY, USA 19 Pages Nirit Binyamini Ben Meir View Details Claims for no evidence also need evidence VM Karhulahti, N Huntington-Klein, N Ballou OSF, 2025 Dr Nick Ballou View Details Towards an Ontology of Wargame Design L Ouriques, CE Barbosa, J Kritz, G Xexéo IEEE Access, vol. 13 Joshua Kritz View Details From social media to artificial intelligence: improving research on digital harms in youth KL Mansfield, S Ghai, T Hakman, N Ballou, M Vuorre, AK Przybylski The Lancet Child & Adolescent Health, Volume 9, Issue 3p194-204, 2025 Dr Nick Ballou View Details When 1+ 1 does not equal 2: Synergy in games Joshua Kritz, Raluca Gaina arXiv preprint arXiv:2502.10304 Joshua Kritz View Details Scaling Analysis of Creative Activity Traces via Fuzzy Linkography A Smith, BR Anderson, JT Otto, I Karth, Y Sun, JJY Chung, M Roemmele, .. Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems Amy Smith View Details "Leave our kids alone!": Exploring Concerns Reported by Parents in 1-star Reviews L Winter, L Helsby, D Zendle CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Article No.: 1036, Pages 1 - 16 Lauren Winter Laura Helsby View Details UKRN Local Network Lead Guidebook UKR Network, SJ Westwood, DL Hird, N Ballou, M Belyk, C Bokhove, ... OSF Preprints, 2025 Dr Nick Ballou View Details XAIxArts Manifesto: Explainable AI for the Arts N Bryan-Kinns, SJ Zheng, F Castro, M Lewis, JR Chang, G Vigliensoni, ... arXiv preprint arXiv:2502.21220, 2025 Dr Terence Broad View Details Archaeological Gameworld Affordances: A Grounded Theory of How Players Interpret Environmental Storytelling F Smith Nicholls, M Cook CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan, Article no 465, p. 1 - 20 Florence Smith Nicholls View Details Reliving 10 years old: Descriptive Insights into Retro Gaming N Ballou, N Bowman, T Hakman, AK Przybylski OSF, 2025 Dr Nick Ballou View Details Seeding for Success: Skill and Stochasticity in Tabletop Games J Goodman, D Perez-Liebana, S Lucas IEEE Transactions on Games, 2025 Dr James Goodman View Details Efficient solutions for an intriguing failure of llms: Long context window does not mean LLMs can analyze long sequences flawlessly Peyman Hosseini, Ignacio Castro, Iacopo Ghinassi, Matthew Purver 31st International Conference on Computational Linguistics (COLING) Peyman Hosseini View Details Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces A Smith, BR Anderson, JT Otto, I Karth, Y Sun, JJY Chung, M Roemmele, ... arXiv preprint arXiv:2502.04599 Amy Smith View Details Formal Constraints and Creativity: Connecting Game Jams, Dogma ’95, the Demo Scene, OuBaPo, and Renga poets G Lai, I Vecchi Games and Culture, 2024 Gorm Lai View Details Using Virtual Reality to Investigate the Influence of Sleep Deprivation on In-the-Moment Arousal During Exposure to Prolonged Threats E Sullivan, C McCall, LM Henderson, M Croissant, G Schofield, S Cairney JOURNAL OF SLEEP RESEARCH 33, 2024 Dr Maximilian Croissant View Details Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents D Jeurissen, D Perez-Liebana, J Gow, D Cakmak, J Kwan arXiv preprint arXiv:2403.00690, 2024 Dominik Jeurissen View Details Climate Club: A Group-based Game to Support Sensemaking of Climate Actions P Sandbhor, J Hook FDG '24: Proceedings of the 19th International Conference on the Foundations of Digital Games, Article No.: 32, Pages 1 - 12, 2024 Prasad Sandbhor Prasad Sandbhor View Details GeoPos: A Minimal Positional Encoding for Enhanced Fine-Grained Details in Image Synthesis Using Convolutional Neural Networks M Hosseini, P Hosseini arXiv preprint arXiv:2401.01951, 2024 Peyman Hosseini View Details An appraisal-based chain-of-emotion architecture for affective language model game agents M Croissant, M Frister, G Schofield, C McCall Plos one 19 (5), e0301033, 2024 Dr Maximilian Croissant Dr Madeleine Frister View Details Use of Technology in Brief Interventions L Gega, MJ Saiger Brief CBT and Science-Based Tailoring for Children, Adolescents, and Young Adolescents, and Young Adults, Springer, pp 293-309, 2024 Michael John Saiger View Details Contextual design requirements for decision-support tools involved in weaning patients from mechanical ventilation in intensive care units N Hughes, Y Jia, M Sujan, T Lawton, I Habli, J McDermid Applied Ergonomics 118, 104275, 2024 Dr Nathan Hughes View Details Affective Systems: Progressing Emotional Human-Computer Interactivity with Adaptive and Intelligent Game Systems M Croissant University of York, 2024 Dr Maximilian Croissant View Details View More