Di Yin

RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction

Yuan Liang, Zhuoxuan Jiang, Di Yin, 2022, ArXiv.

OS-MSL: One Stage Multimodal Sequential Link Framework for Scene Segmentation and Classification

Lingfeng Qiao, Deqiang Jiang, Bo Ren, 2022, ACM Multimedia.

Contrastive Graph Multimodal Model for Text Classification in Videos

Chang-Tien Lu, Bo Ren, Di Yin, 2022, ArXiv.

Unsupervised Extractive Summarization with Heterogeneous Graph Embeddings for Chinese Document

Di Yin, Chen Lin, Ye Liu, 2022, ArXiv.

Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning

Shanshan Feng, Lingfeng Qiao, Zhuoxuan Jiang, 2022, AACL.

Grafting Pre-trained Models for Multimodal Headline Generation

Chen Wu, Lingfeng Qiao, Di Yin, 2022, EMNLP.

MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation

Yulan He, Mingbao Lin, Yunsheng Wu, 2023, ArXiv.

OSAN: A One-Stage Alignment Network to Unify Multimodal Alignment and Unsupervised Domain Adaptation

Chang-Tien Lu, Lingfeng Qiao, Di Yin, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation

Yixuan Yuan, Luping Zhou, Zhen Zhao, 2023, ArXiv.