Valentas Gružauskas

Vilnius University is offering a Postdoctoral Fellowship in Uncertainty-Aware Foundation Models for Earth Observation at the Institute of Computer Science, Faculty of Mathematics and Informatics, within the AI Methods Lab in Vilnius, Lithuania. The project focuses on research into uncertainty-aware foundation models and vision-language models for Earth observation, multi-task environmental monitoring, and trustworthy geospatial AI. The successful candidate will work on methods for making large-scale environmental models not only accurate, but also reliable and well-calibrated. Research directions include deep ensembles, Bayesian and evidential approaches, conformal prediction, and post-hoc calibration; adaptation and benchmarking of Earth observation foundation and vision-language models; and multi-task applications such as land-cover mapping, semantic segmentation, classification, change detection, and climate-related analyses. The fellowship is hosted in a multidisciplinary and collaborative environment with international partners. The postdoctoral researcher will work with heterogeneous remote sensing and in-situ data, including Sentinel, Landsat, and MODIS archives, along with environmental variables, geospatial metadata, and sensor/IoT streams. The project also emphasizes robustness, transferability, and uncertainty calibration across tasks, sensors, regions, and changing acquisition conditions. Supervision is planned by Assoc. Prof. Dr. Valentas Gružauskas , with collaboration possibilities involving Assoc. Prof. Linas Petkevičius . The research group is based at the AI Methods Lab and is connected to work on remote sensing and new foundation vision-language models. The broader context includes reproducible experimentation, HPC-based PyTorch pipelines, open-source release, and scientific publication in high-impact venues. This is a full-time temporary postdoc position for 12 months . The monthly salary is €3,634.00 gross before tax. Candidates must be able to work in Lithuania at the premises of Vilnius University; remote-only candidates will not be considered. Eligibility requirements include a doctoral degree, preferably awarded by a foreign institution or by a Lithuanian science institution other than Vilnius University, and the PhD must normally have been awarded no more than five years ago (with formal extensions possible for documented parental leave). Applicants should have strong expertise in deep learning, computer vision, remote sensing, or multimodal AI, plus experience with Python, PyTorch, satellite imagery or geospatial data, and English at B2 level or higher. Publications in machine learning, AI, or computer vision are expected. Experience in mentoring or grant writing is an advantage. Applications must be submitted by email with the official Vilnius University application form and mandatory attachments: CV, list of publications (up to 10 key items), and a copy of the PhD diploma. The email subject line must state exactly postdoctoral fellowship . Application deadline: 7 September 2026, 23:59 (Europe/Vilnius).

Vilnius University is offering a 12-month postdoctoral fellowship in Predictive World Models for Image Generation within the AI Methods Lab at the Institute of Computer Science, Faculty of Mathematics and Informatics. The project sits in the broad area of computer science and informatics, with a strong emphasis on deep learning, self-supervised learning, generative modelling, and multimodal AI. The successful candidate will work on methods that predict future visual states in latent space and then render them as high-fidelity images, with applications to large-scale image collections such as satellite image time series. The research agenda includes self-supervised joint-embedding predictive architectures, latent-space forecasting, conditioned diffusion, flow matching, and other techniques for controllable visual generation. The postdoctoral fellow will also investigate how to combine world models with generative backbones, how to use vision-language and structural conditioning signals, and how to improve long-horizon consistency, robustness, and evaluation methodology. The work is methodological, but it is grounded in practical experimentation on large image datasets and implemented in reproducible PyTorch-based pipelines on HPC infrastructure. Supervision is planned by Assoc. Prof. Dr. Valentas Gružauskas and Assoc. Prof. Dr. Linas Petkevičius . The postdoctoral fellow will join a collaborative and international research environment, with opportunities to contribute to scientific publications, conference presentations, open-source software, and competitive research proposals. The advertisement also highlights mentoring and knowledge-transfer activities, including support for student projects and lab seminars. The fellowship is full-time, with a gross monthly salary of €3,634 . The contract duration is 12 months , and candidates must be able to work on site in Vilnius, Lithuania. Eligible applicants must hold a doctoral degree, preferably from a foreign institution, or from another Lithuanian science institution outside Vilnius University. As a postdoctoral fellowship, it is targeted at researchers within five years of PhD award, with possible extensions for documented parental leave. Strong preparation in deep learning, computer vision, generative modelling, Python, PyTorch, self-supervised learning, and English communication is expected. Applications must be submitted by email to mokslo.prodekanas@mif.vu.lt with the subject line "postdoctoral fellowship" . The required package includes the official application form, CV, list of up to 10 key publications or patents, and a digital copy of the PhD diploma. The deadline is 7 September 2026 .