Zixuan Ni — accepted AI-conference papers

2026

Beyond Sequential Tools: A Unified VLM Agent System for Photographic Post-Processing via Dynamic Multi-Expert Fusion

Honglin Xiong, Chenjie Zhu, Jianbiao Ding, Zixuan Ni, Wei Li, Zhenpeng Mi +1

CVPR 2026

Real-world image restoration is challenged by complex, coupled degradations. Existing "all-in-one" models often lack generalization, while agentic systems suffer from inefficient sequential tool invocation. We propose a VLM-guided one-shot framework for universal photographic post-processing. Our sy

Cited by 0 Source ↗code ↗Scholar ↗

2023

Continual Vision-Language Representation Learning with Off-Diagonal Information

Zixuan Ni, Longhui Wei, Siliang Tang, Yueting Zhuang, Qi Tian

ICML 2023poster

Large-scale multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. However, these samples are always collected continuously in real scenarios. This paper discusses the feasibility of continual CLIP training using streaming data. Unl…

Cited by 23 Source ↗PDF ↗Scholar ↗