Chunzhi Gu — accepted AI-conference papers

2026

EVLF: Early Vision-Language Fusion for Generative Dataset Distillation

Wenqi Cai, Yawen Zou, Guang Li, Chunzhi Gu, Chao Zhang

CVPR 2026

Dataset distillation (DD) aims to synthesize compact training sets that enable models to achieve high accuracy with significantly fewer samples. Recent diffusion-based DD methods commonly introduce semantic guidance through late-stage cross-attention, where textual prompts tend to dominate the gener

Cited by 0 Source ↗code ↗Scholar ↗

2026

InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models

Shunsuke Sakai, Xiangteng He, Chunzhi Gu, Leonid Sigal, Tatsuhito Hasegawa

CVPR 2026

Despite the remarkable success, recent reconstruction-based anomaly detection (AD) methods via diffusion modeling still involve fine-grained noise-strength tuning and computationally expensive multi-step denoising, leading to a fundamental tension between fidelity and efficiency. In this paper, we p

Cited by 0 Source ↗code ↗Scholar ↗