About
Research & Development
Unlocking Speed in Diffusion-Based Voice Conversion with FasterVoiceGrad
TLDR: FasterVoiceGrad is a novel voice conversion model that dramatically accelerates the conversion process by simultaneously distilling both the main diffusion model and the...
Research & Development
Efficient Voice Conversion: A New Discriminator Reduces Training Time and Memory
TLDR: A new method called Vocoder-Projected Feature Discriminator (VPFD) significantly improves the efficiency of training high-quality voice conversion and text-to-speech models. By using intermediate...
Research & Development
How Large Language Models Build Words from Subword Pieces: Unpacking Compositional Strategies
TLDR: This research paper investigates how Large Language Models (LLMs) compose meaningful word representations from subword units. Through geometry analysis and probing tasks, the...
Research & Development
Adapting Anomaly Detection for Dynamic Medical Imaging
TLDR: This research introduces the first application of Continual Learning (CL) to Visual Anomaly Detection (VAD) in the medical domain. It addresses the challenge...
Research & Development
Large Language Models for Identifying Entities in Historical Documents
TLDR: This research explores using Large Language Models (LLMs) for Named Entity Recognition (NER) in historical texts, which traditionally lack annotated data. The study...
Research & Development
Assessing AI Code Security: Introducing A.S.E, a New Benchmark for Real-World Vulnerabilities
TLDR: A.S.E (AI Code Generation Security Evaluation) is a new, repository-level benchmark designed to rigorously evaluate the security of AI-generated code. It uses real-world...