EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

1 code implementation • 21 Apr 2025 • Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang

In addition, we provide a demo video at https://zjunlp. github. io/project/EasyEdit2/video for a quick introduction.

Language Modeling Language Modelling +1

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

1 code implementation • 27 Mar 2025 • Haoming Xu, Shuxun Wang, Yanqiu Zhao, Yi Zhong, Ziyan Jiang, Ningyuan Zhao, Shumin Deng, Huajun Chen, Ningyu Zhang

This paper presents the ZJUKLAB team's submission for SemEval-2025 Task 4: Unlearning Sensitive Content from Large Language Models.

SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning

1 code implementation • 15 Nov 2024 • Zewen Chen, Juan Wang, Wen Wang, Sunhan Xu, Hang Xiong, Yun Zeng, Jian Guo, Shuxun Wang, Chunfeng Yuan, Bing Li, Weiming Hu

The quality analysis of ROIs can provide fine-grained guidance for image quality improvement and is crucial for scenarios focusing on region-level quality.

Language Modeling Language Modelling +1

NFT1000: A Cross-Modal Dataset for Non-Fungible Token Retrieval

1 code implementation • 29 Jan 2024 • Shuxun Wang, Yunfei Lei, Ziqi Zhang, Wei Liu, Haowei Liu, Li Yang, Wenjuan Li, Bing Li, Weiming Hu

In this paper, we will introduce a benchmark dataset named "NFT Top1000 Visual-Text Dataset" (NFT1000), containing 7. 56 million image-text pairs, and being collected from 1000 most famous PFP1 NFT collections2 by sales volume on the Ethereum blockchain.

Retrieval