Search Results for author:
Found 12 papers, 2 papers with code
Controlled Automatic Task-Specific Synthetic Data Generation for Hallucination Detection
Hallucination pattern guidance leverages the most important task-specific hallucination patterns while language style alignment aligns the style of the synthetic dataset with benchmark text.
Learning from Contrastive Prompts: Automated Optimization and Adaptation
As LLMs evolve, significant effort is spent on manually crafting prompts.
Efficient Continual Pre-training for Building Domain Specific Large Language Models
We further explore simple but effective data selection strategies for continual pre-training.
Embarrassingly Simple MixUp for Time-series
Labeling time series data is an expensive task because of domain expertise and dynamic nature of the data.
Filling out the missing gaps: Time Series Imputation with Semi-Supervised Learning
Our results indicate that the proposed method outperforms the existing supervised and unsupervised time series imputation methods measured on the imputation quality as well as on the downstream tasks ingesting imputed time series.
Using Clinical Notes with Time Series Data for ICU Management
Monitoring patients in ICU is a challenging and high-cost task.
Benchmarking Regression Methods: A comparison with CGAN
Such a real world situation is best represented using an implicit model in which an extra noise vector, $z$ is included with $x$ as input.
Optimizing the Linear Fascicle Evaluation Algorithm for Multi-Core and Many-Core Systems
Among recent representation techniques, tensor decomposition is a popular one used for very large but sparse matrices.
Two Birds with One Network: Unifying Failure Event Prediction and Time-to-failure Modeling
Classically, this problem has been posed in two different ways which are typically solved independently: (1) Remaining useful life (RUL) estimation as a long-term prediction task to estimate how much time is left in the useful life of the equipment and (2) Failure prediction (FP) as a short-term prediction task to assess the probability of a failure within a pre-specified time window.
Adversarial Unsupervised Representation Learning for Activity Time-Series
Sufficient physical activity and restful sleep play a major role in the prevention and cure of many chronic conditions.
A Structured Learning Approach with Neural Conditional Random Fields for Sleep Staging
We propose an end-to-end framework that uses a combination of deep convolution and recurrent neural networks to extract high-level features from raw flow signal with a structured output layer based on a conditional random field to model the temporal transition structure of the sleep stages.
Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning
This is a critical barrier for the use of this new source of signal for healthcare decision making.
