Jiangjiang Liu — accepted AI-conference papers

2025

Continual SFT Matches Multimodal RLHF with Negative Supervision

Ke Zhu, Yu Wang, Yanpeng Sun, Qiang Chen, Jiangjiang Liu, Gang Zhang +1

CVPR 2025poster

Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this paper, we observe that the inherent value of multi…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models

Sifan Long, Zhen Zhao, Junkun Yuan, Zichang Tan, Jiangjiang Liu, Luping Zhou +2

ICCV 2023poster

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an appropriate prompt for each specific task. Recent CoCoOp further boo…

Cited by 6 PDF ↗Scholar ↗