Counterfactual inference enables clinicians to ask 'what if' questions about patient outcomes, but standard methods assume feature independence and simultaneous...
Patient-generated text such as secure messages, surveys, and interviews contains rich expressions of the patient voice (PV), reflecting communicative behaviors ...
In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mu...
Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Al...
Accurate interpretation of electrocardiogram (ECG) signals is crucial for diagnosing cardiovascular diseases. Recent multimodal approaches that integrate ECGs w...
Selective state space models (SSMs) have rapidly become a compelling backbone for large language models, especially for long-context workloads. Yet in deploymen...
Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis...
As LLM deployments scale over more hardware, the probability of a single failure in a system increases significantly, and cloud operators must consider robust c...
Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. Th...
Customer-provided reviews have become an important source of information for business owners and other customers alike. However, effectively analyzing millions ...
The analyzability of hybrid software, which integrates both classical and quantum components, is a key factor in ensuring its maintainability and industrial ado...
Large Language Models (LLMs) are transforming scholarly tasks like search and summarization, but their reliability remains uncertain. Current evaluation metrics...
