Latest AI and machine learning research in staffing & scheduling for healthcare professionals.
Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed as the inverse of learning, using gradient-based updates to reduce the influence of a forget-set by counteracting the previously learned behavior. Recently, Muon, a gradient descent variant, has been introduced. Muon applies spectral magnitude normal...
Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation. This motivates careful analysis of how VLMs process visual and textual information. In this work, we study how VLMs interpret text rendered as an image, and investigate the influence of visual styling biases. To this end, we introduce Stealth Visual Prompts, wh...
Deep representation learning has primarily focused on how features evolve across network layers, while largely overlooking the structured geometry emb...
Falls are a major health concern for older adults, and wearable sensors have been widely explored for detecting falls and enabling timely intervention...
Deep networks segment brain tumours accurately in-distribution, but can fail silently when the input differs from their training data. That risk is ce...
Text-to-image generative models have advanced rapidly, with modern Diffusion Transformer architectures producing images that are increasingly difficul...
Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks wit...
Flow-based generative models have emerged as powerful image priors for training-free inverse problem solving, capturing coherent semantics and fine-gr...
Leukemia cell image classification is challenged by real-world domain shifts from acquisition, staining, illumination, and site protocols, causing sin...
Despite glutamates widespread role as the dominant excitatory transmitter in vertebrate brains, the early evolution of glutamate and its recruitment i...
Unsupervised domain adaptation is a widespread set of methods that leverages the knowledge of a labeled source domain to train a model to perform well...
Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math,...
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-d...
Machine learning models for protein properties are usually reported by a single accuracy figure, which says how a model behaves on average but not whe...
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-d...
Few-shot learning has emerged as a promising approach for anatomical segmentation when labelled data are scarce. However, different few-shot learning ...
Hospitals are rapidly adopting artificial intelligence for triage, imaging, scheduling etc., yet most deployments remain isolated point solutions lock...
Vision transformers (ViTs) have become the de facto standard for image encoding across many perception tasks. Despite their empirical success, it rema...
On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (ML...
Pixel-space diffusion models avoid the reconstruction ceiling of latent diffusion models by generating directly in image space. However, their substan...