Related papers: Improving the modeling of the Agility multi-leaf c…

Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training…

We obtain asymptotically sharp error estimates for the consistency error of the Target Measure Diffusion map (TMDmap) (Banisch et al. 2020), a variant of diffusion maps featuring importance sampling and hence allowing input data drawn from…

In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from diverse domains and…

The development of well-devised irrigation scheduling methods is desirable from the perspectives of plant quality and water conservation. In this article, a model predictive control (MPC) with discrete actuators is developed for irrigation…

Modern LLMs struggle with efficient updates, as each new pretrained model version requires repeating expensive alignment processes. This challenge also applies to domain- or languagespecific models, where fine-tuning on specialized data…

Polymers, integral to advancements in high-tech fields, necessitate the study of their thermal conductivity (TC) to enhance material attributes and energy efficiency. The TC of polymers obtained by molecular dynamics (MD) calculations and…

The aim of the systematic review was to assess recently published studies on diagnostic test accuracy of glioblastoma treatment response monitoring biomarkers in adults, developed through machine learning (ML). Articles were searched for…

We investigate fine-tuning Vision-Language Models (VLMs) for multi-task medical image understanding, focusing on detection, localization, and counting of findings in medical images. Our objective is to evaluate whether instruction-tuned…

Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…

Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the…

By augmenting Large Language Models (LLMs) with external tools, their capacity to solve complex problems has been significantly enhanced. However, despite ongoing advancements in the parsing capabilities of LLMs, incorporating all available…

Tractography is a unique method for mapping white matter connections in the brain, but tractography algorithms suffer from an inherent trade-off between sensitivity and specificity that limits accuracy. Incorporating prior knowledge of…

We propose TG-LMM (Text-Guided Large Multi-Modal Model), a novel approach that leverages textual descriptions of organs to enhance segmentation accuracy in medical images. Existing medical image segmentation methods face several challenges:…

Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs). In practice, LLMs are often required to handle a diverse set of tasks from multiple domains, a scenario naturally addressed by multi-task…

Large language models (LLMs) have demonstrated impressive task-solving capabilities through prompting techniques and system designs, including solving planning tasks (e.g., math proofs, basic travel planning) when sufficient data is…

Determining transition states (TSs) of surface reactions is central to understanding and designing heterogeneous catalysts but remains computationally prohibitive with density functional theory (DFT). While machine learning potentials…

We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business insights, our target use case, requires decomposing it into executable steps over structured tools…

Despite strong performance in many sequence-to-sequence tasks, autoregressive models trained with maximum likelihood estimation suffer from exposure bias, i.e. the discrepancy between the ground-truth prefixes used during training and the…

Detecting out of policy speech (OOPS) content is important but difficult. While machine learning is a powerful tool to tackle this challenging task, it is hard to break the performance ceiling due to factors like quantity and quality…

In recent years, the growing demand for medical imaging diagnosis has placed a significant burden on radiologists. As a solution, Medical Vision-Language Pre-training (Med-VLP) methods have been proposed to learn universal representations…