Latest AI and machine learning research in staffing & scheduling for healthcare professionals.
Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style reference.Despite recent progress, this setting remains challenging because models must balance content fidelity, style alignment, and instruction following avoiding semantic leakage from the style reference.A key bottlen...
Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures. Existing benchmarks for speech-capable models focus on the timing of interruptions: barge-in detection, endpointing, and turn-taking dynamics. They leave unmeasured what happens after the interr...
Importance. Large language models (LLMs) increasingly inform mental health decisions by patients and clinicians. Inference-time activation steering ca...
Traditional CPU, GPU, and NPU architectures are increasingly limited by the von Neumann bottleneck. While In-Memory Computing (IMC) using ReRAM crossb...
Scientific machine-learning (SciML) surrogates approximate expensive simulations, but exact expected outputs for arbitrary inputs are unavailable (the...
When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. Thi...
Post-training quantization (PTQ) enables efficient deployment of deep networks using a small set of data. Its application to visual autoregressive mod...
With new data privacy laws such as the General Data Protection Regulation (GDPR) [1] that allow individuals to ask that any of their personal informat...
Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving k...
Large multimodal language models (LLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic policies. How...
Subject-driven image customization aims to generate images that not only follow textual instructions but also preserve the identity of a given referen...
Pairwise comparison is the gold standard for subjective ranking tasks; however, exhaustive annotation requires a massive number of human comparisons (...
Federated class-incremental learning (FCIL) becomes substantially harder when clients observe different label subsets, progress through tasks at diffe...
Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels inde...
Transfer learning is usually studied as a consequence of distribution shift. This paper identifies an orthogonal failure mode in which the data distri...
Spiking Neural Networks (SNNs) offer a brain-inspired path toward highly efficient computation, but their practical deployment is constrained by the c...
Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving....
Vehicle color recognition is an important cue for vehicle identification in surveillance systems, especially when license plates are illegible due to ...
Flexible, goal-directed behavior depends on the ability to select and prioritize information from memory representations freshly encoded from the sens...
The physical properties of biomolecular condensates, which form through phase separation, are central to their organisation and function and are incre...