no code implementations • 4 May 2024 • Zhihao Wang, Longyue Wang, Jinsong Su, Junfeng Yao, Zhaopeng Tu
By manually annotating the NAT outputs, we identify two types of information redundancy errors that correspond well to lexical and reordering multi-modality problems.
no code implementations • 16 Apr 2024 • Jingze Chen, Junfeng Yao, Qiqin Lin, Lei LI
Occlusions hinder point cloud frame alignment in LiDAR data, a challenge inadequately addressed by scene flow models tested mainly on occlusion-free datasets.
no code implementations • 2 Mar 2024 • Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su
When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent.
no code implementations • 15 Feb 2024 • Yaoxiang Wang, Zhiyong Wu, Junfeng Yao, Jinsong Su
The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks.
no code implementations • 1 Feb 2024 • Weixing Xie, Xiao Dong, Yong Yang, Qiqin Lin, Jingze Chen, Junfeng Yao, Xiaohu Guo
With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology.
no code implementations • 23 Dec 2023 • Jingze Chen, Junfeng Yao, Qiqin Lin, Rongzhou Zhou, Lei LI
This paper introduces SSFlowNet, a semi-supervised approach for scene flow estimation, that utilizes a blend of labeled and unlabeled data, optimizing the balance between the cost of labeling and the precision of model training.
1 code implementation • 25 May 2023 • Zhihao Wang, Longyue Wang, Jinsong Su, Junfeng Yao, Zhaopeng Tu
Experimental results on the large-scale WMT20 En-De show that the asymmetric architecture (e. g. bigger encoder and smaller decoder) can achieve comparable performance with the scaling model, while maintaining the superiority of decoding speed with standard NAT models.
1 code implementation • EMNLP 2021 • Shaopeng Lai, Ante Wang, Fandong Meng, Jie zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang, Jinsong Su
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models.
1 code implementation • Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 2021 • An-Hui Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, Jinsong Su
Conversational discourse structures aim to describe how a dialogue is organised, thus they are helpful for dialogue understanding and response generation.
Ranked #3 on Discourse Parsing on STAC
no code implementations • 31 May 2021 • Binbin Xie, Jinsong Su, Yubin Ge, Xiang Li, Jianwei Cui, Junfeng Yao, Bin Wang
However, such a decoder only exploits the preorder traversal based preceding actions, which are insufficient to ensure correct action predictions.