Wenxu Gao — accepted AI-conference papers

2026

Dual-Path Condition Alignment for Diffusion Transformers

Changhao Peng, Yuqi Ye, Shuangjun Du, Wenxu Gao, Wei Gao

ICLR 2026poster

Denoising-based generative models have been significantly advanced by representation-alignment (REPA) loss, which leverages pre-trained visual encoders to guide intermediate network features. However, REPA's reliance on external visual encoders introduces two critical challenges: potential \textit{d…

Cited by 0 Source ↗code ↗Scholar ↗

2025

VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment

Shangkun Sun, Xiaoyu Liang, Songlin Fan, Wenxu Gao, Wei Gao

AAAI 2025technical

Text-driven video editing has recently experienced rapid development. Despite this, evaluating edited videos remains a considerable challenge. Current metrics tend to fail to align with human perceptions, and effective quantitative metrics for video editing are still notably absent. To address this,…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗