Jihua Zhu

Evaluation and Analysis of Hallucination in Large Vision-Language Models

2023 · arXiv (Cornell University)

Large Vision-Language Models (LVLMs) have recently achieved remarkable success. However, LVLMs are still plagued by the hallucination problem, which limits the practicality in many scenarios. Hallucination refers to the information of LVLMs' responses that does …

VITS-Based Singing Voice Conversion System with DSPGAN Post-Processing for SVCC2023

2023

This paper presents the T02 team’s system for the Singing Voice Conversion Challenge 2023 (SVCC2023). Our system entails a VITS-based SVC model, incorporating three modules: a feature extractor, a voice converter, and a postprocessor. Specifically, …