Dmitry Bagaev | BIASlab

Gaussian variational inference with non-Gaussian factors for state estimation

Mon, 12 Jan 2026 09:00:00 +0200

AIM-TT

Mon, 01 Dec 2025 00:00:00 +0000

AiMTT aims to cultivate a highly skilled and diverse AI talent pool equipped to address the opportunities and challenges of AI in mobility, transport, and logistics. By combining real-world case studies with knowledge development, this initiative fosters deep expertise in the field.

Mobility, transport, and logistics face a multitude of challenges: traffic congestion, livability concerns, conflicts between user, operator, and public interests, space constraints, and safety risks during large-scale events. These challenges are further complicated by their deep interconnections, making them particularly difficult to resolve.

While such complexities can be overwhelming for the human mind, they offer ideal use cases for artificial intelligence (AI). AI can process vast amounts of data in real time, provide accurate network assessments, calculate impacts in future scenarios, and optimize interventions. It also enhances our understanding of human behavior and the mobility system as a whole.

Given these advantages, leveraging AI to address mobility challenges is a logical next step. Through AiMTT, we embrace a “learning by doing” approach to develop responsible, AI-driven solutions.

Vision and Ambition

AiMTT stands for AI Learning Initiative for Multi-modal Traffic and Transportation. It operates under the umbrella of AIC4NL, an organization dedicated to the responsible development and application of AI in the Netherlands. Ensuring responsible AI development is essential, as concerns about fairness, inclusivity, privacy, and human oversight continue to grow. Will AI-generated outcomes be equitable? Can privacy be safeguarded? How do we ensure that humans remain in control?

AiMTT aims to address these critical questions by fostering a collaborative learning community that brings together experts from academia, industry, and government. Project partners will build, test, and refine AI applications, with ethical considerations—such as fairness, privacy, and human autonomy—at the forefront.

Learning Process

AiMTT’s approach is grounded in practical application. AI solutions will be developed through seven real-world use cases, each designed to create tangible tools that can be directly implemented. Equally important is the learning process itself: identifying best practices, analyzing challenges, and refining AI applications based on real-world insights.

To support this, the project will offer workshops, training programs, and co-creation sessions—ensuring continuous knowledge exchange and improvement.

Through AiMTT, we are shaping the future of urban mobility by responsibly integrating AI to create smarter, safer, and more efficient transportation systems.

ExponentialFamilyManifolds.jl: Representing exponential families as Riemannian manifolds

Mon, 14 Apr 2025 16:37:31 +0200

GraphPPL.jl: A Probabilistic Programming Language for Graphical Models

Tue, 22 Oct 2024 09:00:00 +0200

Multi-Agent Trajectory Planning with NUV Priors

Wed, 10 Jul 2024 00:00:00 +0000

Reactive Probabilistic Programming for Scalable Bayesian Inference

Tue, 19 Dec 2023 09:00:00 +0200

Reactive Message Passing for Scalable Bayesian Inference

Sat, 27 May 2023 09:00:00 +0200

RxInfer: A Julia package for reactive real-time Bayesian inference

Thu, 20 Apr 2023 09:00:00 +0200

Message Passing-based Inference in Switching Autoregressive Models

Fri, 02 Sep 2022 00:00:00 +0000

ReactiveMP.jl: A Julia package for reactive variational Bayesian inference

Sun, 01 May 2022 00:00:00 +0000

ReactiveMP.jl: A Julia package for reactive message passing-based Bayesian inference

Sat, 29 Jan 2022 00:00:00 +0000

Message Passing-Based Inference in the Gamma Mixture Model

Mon, 25 Oct 2021 00:00:00 +0000

Variational Message Passing and Local Constraint Manipulation in Factor Graphs

Thu, 24 Jun 2021 16:37:31 +0200

CoHear

Wed, 01 Feb 2017 00:00:00 +0000

Hearing loss is a very serious health condition that has been associated with early dementia and cognitive decline. Still, hearing aid market penetration is quite low, in particular for the large population that is afflicted with ‘mild-to-moderate’ hearing impairment. This is mainly due to two reasons: Stigma (association with old age) and hearing aids (HA) sound quality. The recent commercial introduction of fashionable ‘hearables’ will likely alleviate the stigma issue. Recent advances in machine learning and cloud computing open new avenues for attacking the sound quality issue for hearing aids. In this project, we intend to develop a (crowd-based) collaborative design approach to improving the sound quality issues for the mild-to-moderately hearing-impaired population.

We expect to build a working prototype for collaboratively designed hearing algorithms that can be applied to a new class of ‘smart hearing devices’ with high appeal to the mild-to-moderately hearing-impaired patient. As an additional benefit, we hope that our technology will ease the transition from hearables to professional hearing aid technology for the moderate-to-profound hearing-impaired population.