About
Research & Development
Teaching Musical Agents to Understand Song Structure Through Deep Learning
TLDR: This research introduces a novel deep learning architecture for musical agents that learns musical relationships between separate audio tracks (stems) from examples, rather...
Research & Development
TDDev: Building Full-Stack Web Apps Automatically with AI
TLDR: TDDev is a new AI framework that automates the entire process of generating full-stack web applications from user requirements. It uses three specialized...
Research & Development
Evaluating Language Model Text Quality Through Internal Geometric Properties
TLDR: This research introduces a novel, reference-free method for evaluating the quality and naturalness of text generated by large language models (LLMs). Instead of...
Research & Development
Unveiling AI’s Moral Choices: A New Approach to Understanding Language Model Values
TLDR: A new research paper introduces CONFLICTSCOPE, an automated system to create and evaluate scenarios where large language models (LLMs) face conflicts between different...
Research & Development
Enhancing Language Models with Critical Thinking for Accurate Answers
TLDR: The research introduces the Thinking-supervised Reward Model (TRM), a novel framework designed to imbue large language models (LLMs) with critical thinking abilities. TRM...
Research & Development
Advancing Emotional Text-to-Speech with Stepwise Preference Optimization
TLDR: Emotion-Aware Stepwise Preference Optimization (EASPO) is a new post-training framework for diffusion text-to-speech models that significantly enhances emotional expressiveness and naturalness. It introduces...