Tim Van de Cruys

KU Leuven is offering a PhD position in Tensor Factorization Models for Creative Language Generation within the ERC Consolidator Grant project TENACITY (Tensors and Neural Networks for Computational Creativity). The project is hosted by the Centre for Computational Linguistics (CCL) , part of the ComForT research unit at KU Leuven, in Leuven, Belgium. The position focuses on the tensor-based strand of TENACITY, which investigates how computational models can generate more creative language. The research goal is to derive interpretable latent semantic dimensions from multi-way word co-occurrences and manipulate these dimensions to produce creative language expressions. The successful candidate will join a team of PhD researchers and postdocs working on computational creativity, with an opportunity to extend current work on metaphor into broader creative language phenomena. Possible research directions include efficient factorization algorithms for large-scale sparse language data, such as tensor train decomposition, the automatic induction of semantic domain mappings, and the application of latent semantic structure to creative language generation. The precise topic will be shaped by the candidate’s background and interests. The position is well suited to candidates with training in computational linguistics, artificial intelligence, computer science, mathematics, or a related field. A solid background in machine learning, linear algebra, and programming is expected; experience with tensor methods is an advantage. The project also calls for a strong interest in language, lexical semantics, and figurative language, together with excellent English and strong communication skills. This is a full-time PhD post with an initial duration of one year, extendable up to four years after a positive evaluation. The project is ERC-funded and provides access to computing infrastructure, funding for conference travel, and academic training opportunities including international conferences and workshops. The application deadline is 2026-08-10 23:59 (Europe/Brussels). Applications should be submitted via the KU Leuven job portal.

KU Leuven is recruiting a PhD student for the ERC Consolidator Grant project TENACITY (Tensors and Neural Networks for Computational Creativity), based at the Centre for Computational Linguistics (CCL) within the ComForT research unit. The project explores how language technology can exhibit creativity, combining tensor factorization methods with neural language models. This specific PhD position focuses on the neural strand of the project, with an emphasis on constraint-based neural network architectures for creative language generation. The research goal is to develop methods for integrating constraints into transformer-based language models so that generation becomes more novel and expressive while preserving meaning. The work will be informed by latent semantic representations developed in TENACITY and will contribute to broader research on computational creativity, NLP, and language generation. The exact research focus can be shaped by the candidate’s background and interests. You will join the TENACITY team of PhD researchers and postdocs at KU Leuven’s Centre for Computational Linguistics and work in a high-level research environment with access to substantial computing infrastructure. The position is part of an ERC-funded project and includes funding for conference travel, with opportunities to attend international conferences, workshops, and academic training activities. Applicants should hold a Master’s degree in artificial intelligence, computational linguistics, computer science, or a related equivalent qualification. Strong experience with neural networks and deep learning for NLP is required, along with a good understanding of current large language model architectures. Programming skills, preferably in Python and PyTorch, are important, as are strong English communication skills and a clear interest in language, linguistics, and computational creativity. This is a full-time PhD position offered initially for 1 year and extendable to 4 years after a positive evaluation. The application deadline is 2026-08-10. The position is based in Leuven, Belgium, at KU Leuven.

KU Leuven is recruiting a postdoctoral researcher for the ERC Consolidator Grant project TENACITY (Tensors and Neural Networks for Computational Creativity) at the Centre for Computational Linguistics (CCL) , part of the ComForT research unit . The project explores computational models of language that exhibit creativity, with a specific focus on integrating latent factorization models and neural language models for creative language generation. The research agenda brings together two complementary lines of work: interpretable tensor factorization models that induce latent semantic structure from multi-way word co-occurrences, and constraint-based neural language models designed to steer generation toward creative output. The successful candidate will help build an integrated framework in which latent structure from factorization models informs the latent representations of transformer-based language models, potentially through variational inference approaches. The goal is to better control and understand latent variables so they can be used for creative generation, including tasks such as producing text in a particular style or other expressive forms of language use. This is a challenging high-risk/high-gain project with substantial freedom for the postdoctoral researcher to shape the research direction according to their expertise and vision. The position is research-only and has no teaching obligations. Responsibilities include developing variational inference methods for transformer-based language models informed by tensor factorization structure; investigating interpretability of the latent space and its use for creative language generation such as metaphor and style; collaborating closely with the project’s PhD students and providing day-to-day guidance; and publishing results in top NLP and machine learning venues and presenting at international conferences. Profile : applicants should hold a PhD in natural language processing, machine learning, computational linguistics, or a related field, ideally with peer-reviewed publications. Strong deep learning expertise in NLP is expected, along with a strong plus for experience in latent variable models and/or variational inference. The role also requires excellent Python and PyTorch programming skills, experience with large-scale experimentation on GPU infrastructure, and strong English communication skills. Experience guiding junior researchers is welcome. Offer and funding : the position is full-time for 2 years in a high-level ERC-funded research environment, with access to ample computing infrastructure and funding for conference travel. KU Leuven emphasizes an inclusive and respectful environment and encourages applications from diverse candidates. Application and deadline : apply via the KU Leuven jobsite link. The application deadline is 2026-08-10 23:59 (Europe/Brussels).