Valentio Iverson

2 accepted papers

2026

The Accumulation of Score Estimation Error in Diffusion Models

Baoxiang He, Valentio Iverson, Shuai Li, Cheng Chen, Bo Jiang

ICML 2026poster

Diffusion models are widely used for high-quality generation, but their performance is sensitive to the accuracy of the estimated score. We first develop our main bounds in a Gaussian-mixture setting, where the score admits a closed-form structure and the score Hessian can be controlled explicitly, …

Cited by 0 Source ↗Scholar ↗

2025

LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport

Kyeongha Rho, Hyeongkeun Lee, Valentio Iverson, Joon Son Chung

ICASSP 2025accepted

Automated audio captioning is a task that generates textual descriptions for audio content, and recent studies have explored using visual information to enhance captioning quality. However, current methods often fail to effectively fuse audio and visual data, missing important semantic cues from eac…

Cited by 0 Source ↗Scholar ↗