Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem...
We present NordFKB, a fine-grained benchmark dataset for geospatial AI in Norway, derived from the authoritative, highly accurate, national Felles KartdataBase ...
In-context learning with attention enables large neural networks to make context-specific predictions by selectively focusing on relevant examples. Here, we ada...
Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This ...
Reinforcement learning agents often behave unexpectedly in sparse-reward or safety-critical environments, creating a strong need for reliable debugging and veri...
Moralisation and Triangulation are transformations allowing to switch between different ways of factoring a probability distribution into a graphical model. Mor...
Vision-Language Models (VLMs) have achieved impressive progress in perceiving and describing visual environments. However, their ability to proactively reason a...
Visual navigation has emerged as a practical alternative to traditional robotic navigation pipelines that rely on detailed mapping and path planning. However, c...
Backpressure (BP) routing and scheduling is an established resource allocation method for wireless multi-hop networks, noted for its fully distributed operation...
The integration of Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) is increasingly central to the development of intelligent autonomous syst...
Long-term planning in complex, text-based environments presents significant challenges due to open-ended action spaces, ambiguous observations, and sparse feedb...
Metadata vocabularies are essential for advancing FAIR and FARR data principles, but their development constrained by limited human resources and inconsistent s...
Recent advances in protein language models (PLMs) have demonstrated remarkable capabilities in understanding protein sequences. However, the extent to which dif...
While modern language models and their inner workings are incredibly complex, recent work (Golowich, Liu & Shetty; 2025) has proposed a simple and potential...
We analyze the distinctions between two functionals often used as over-smoothing measures: the Dirichlet energies induced by the unnormalized graph Laplacian an...
Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requir...
Correctly parsing mathematical formulas from PDFs is critical for training large language models and building scientific knowledge bases from academic literatur...
Linear spectral mixture models (LMM) provide a concise form to disentangle the constituent materials (endmembers) and their corresponding proportions (abundance...
Pretrained Multimodal Large Language Models (MLLMs) are increasingly deployed in medical AI systems for clinical reasoning, diagnosis support, and report genera...
Large language models (LLMs) increasingly mediate human communication, decision support, content creation, and information retrieval. Despite impressive fluency...
We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making ...
Time awareness is a fundamental ability of omni large language models, especially for understanding long videos and answering complex questions. Previous approa...
Learning models over factorized joins avoids redundant computations by identifying and pre-computing shared cofactors. Previous work has investigated the perfor...
This chapter explores the application of Large Language Models in the legal domain, showcasing their potential to optimise and augment traditional legal tasks b...
