Machine learning/ Deep learning
4 Results were found on Technologies
Sub Category Name
Execution Guided Line-by-Line Code Generation
Large language models (LLMs) have revolutionized the field of code generation, demonstrating impressive capabilities in automating programming tasks and assisting developers. Despite these advancements, current methods primarily rely on pattern recognition from static code representations, often producing syntactically plausible but functionally incorrect code. Many of these models lack the ability to explicitly reason about runtime […] Read More >
Overclocking LLM Reasoning- Monitoring and Controlling Thinking Path Lengths in LLMs
Large Language Models (LLMs) like ChatGPT have revolutionized AI-powered reasoning, enabling applications across diverse domains. However, their internal reasoning processes often remain opaque, leaving users in the dark about how long the model will take to arrive at an answer. UNMET NEED Currently, users interact with reasoning models without any indication of the internal progress […] Read More >
Using Eye-Tracking in VR to Identify Subject Preferences to Optimize Personalization
The implementation of virtual reality (VR) has been spreading in many research fields and healthcare applications. In order to better personalize the presented content, there is a need to identify the subjective experience at each time point. Previous studies with eye-tracking (ET) have demonstrated its links to preferences; therefore, collecting ET data during VR experiences […] Read More >
Leveraging Gene Panel Sequencing Data for Mutational Signature Analysis with Applications to Personalized Treatment
UNMET NEED Mutational signatures and their exposures are key to understanding the processes that shape cancer genomes with applications to diagnosis and treatment. Yet current signature analysis approaches are limited to relatively rich mutation data that comes from whole-genome or whole-exome sequencing. Recently, orders of magnitude sparser data sets from gene panel sequencing have become […] Read More >
