1 code implementation • 25 Feb 2024 • Xinze Li, Zhenghao Liu, Chenyan Xiong, Shi Yu, Yukun Yan, Shuo Wang, Ge Yu
It finetunes the compression plugin module and uses the representations of gist tokens to emulate the raw prompts in the vanilla language model.
1 code implementation • 22 Feb 2024 • Zhipeng Xu, Zhenghao Liu, Yukun Yan, Zhiyuan Liu, Chenyan Xiong, Ge Yu
The web contains large-scale, diverse, and abundant information to satisfy the information-seeking needs of humans.
1 code implementation • 21 Feb 2024 • Zhipeng Xu, Zhenghao Liu, Yibin Liu, Chenyan Xiong, Yukun Yan, Shuo Wang, Shi Yu, Zhiyuan Liu, Ge Yu
Retrieval Augmented Generation (RAG) has introduced a new paradigm for Large Language Models (LLMs), aiding in the resolution of knowledge-intensive tasks.
no code implementations • 27 Jan 2024 • Pengjie Liu, Zhenghao Liu, Xiaoyuan Yi, Liner Yang, Shuo Wang, Yu Gu, Ge Yu, Xing Xie, Shuang-Hua Yang
It proposes a dual-view legal clue reasoning mechanism, which derives from two reasoning chains of judges: 1) Law Case Reasoning, which makes legal judgments according to the judgment experiences learned from analogy/confusing legal cases; 2) Legal Ground Reasoning, which lies in matching the legal clues between criminal cases and legal decisions.
no code implementations • 21 Jan 2024 • Zhigang Wang, Hangyu Yang, Ning Wang, Chuanfei Xu, Jie Nie, Zhiqiang Wei, Yu Gu, Ge Yu
However, training its complex network is very space-consuming, since a lot of intermediate data are preserved across layers, especially when processing high-dimension inputs with a big batch size.
no code implementations • 5 Dec 2023 • Chaoyi Chen, Dechao Gao, Yanfeng Zhang, Qiange Wang, Zhenbo Fu, Xuecang Zhang, Junhua Zhu, Yu Gu, Ge Yu
Though many dynamic GNN models have emerged to learn from evolving graphs, the training process of these dynamic GNNs is dramatically different from traditional GNNs in that it captures both the spatial and temporal dependencies of graph updates.
no code implementations • 22 Nov 2023 • Hao Yuan, Yajiong Liu, Yanfeng Zhang, Xin Ai, Qiange Wang, Chaoyi Chen, Yu Gu, Ge Yu
Many Graph Neural Network (GNN) training systems have emerged recently to support efficient GNN training.
no code implementations • 22 Nov 2023 • Xin Ai, Qiange Wang, Chunyu Cao, Yanfeng Zhang, Chaoyi Chen, Hao Yuan, Yu Gu, Ge Yu
After extensive experiments and analysis, we find that existing task orchestrating methods fail to fully utilize the heterogeneous resources, limited by inefficient CPU processing or GPU resource contention.
1 code implementation • 16 Nov 2023 • Hanbin Wang, Zhenghao Liu, Shuo Wang, Ganqu Cui, Ning Ding, Zhiyuan Liu, Ge Yu
INTERVENOR prompts Large Language Models (LLMs) to play distinct roles during the code repair process, functioning as both a Code Learner and a Code Teacher.
Ranked #16 on Code Generation on HumanEval
no code implementations • 12 Nov 2023 • Zhenghao Liu, Zulong Chen, Moufeng Zhang, Shaoyang Duan, Hong Wen, Liangyue Li, Nan Li, Yu Gu, Ge Yu
This paper proposes the User Viewing Flow Modeling (SINGLE) method for the article recommendation task, which models the user constant preference and instant interest from user-clicked articles.
1 code implementation • 21 Oct 2023 • Tianshuo Zhou, Sen Mei, Xinze Li, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Ge Yu
To facilitate the multi-modal retrieval tasks, we build the ClueWeb22-MM dataset based on the ClueWeb22 dataset, which regards anchor texts as queries, and exacts the related text and image documents from anchor-linked web pages.
1 code implementation • 27 Aug 2023 • Zhenghao Liu, Sen Mei, Chenyan Xiong, Xiaohua LI, Shi Yu, Zhiyuan Liu, Yu Gu, Ge Yu
TASTE alleviates the cold start problem by representing long-tail items using full-text modeling and bringing the benefits of pretrained language models to recommendation systems.
1 code implementation • 31 May 2023 • Xinze Li, Zhenghao Liu, Chenyan Xiong, Shi Yu, Yu Gu, Zhiyuan Liu, Ge Yu
SANTA proposes two pretraining methods to make language models structure-aware and learn effective representations for structured data: 1) Structured Data Alignment, which utilizes the natural alignment relations between structured data and unstructured data for structure-aware pretraining.
no code implementations • 10 Mar 2023 • Yumeng Song, Yu Gu, Tianyi Li, Jianzhong Qi, Zhenghao Liu, Christian S. Jensen, Ge Yu
However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data.
no code implementations • 17 Feb 2023 • Hengyu Liu, Tiancheng Zhang, Fan Li, Minghe Yu, Ge Yu
To better model students' exercise responses, we proposed a logarithmic linear model with three interactive strategies, which models students' exercise responses by considering the relationship among students' knowledge status, knowledge concept, and problems.
1 code implementation • 1 Sep 2022 • Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, Ge Yu
To learn a unified embedding space for multi-modal retrieval, UniVL-DR proposes two techniques: 1) Universal embedding optimization strategy, which contrastively optimizes the embedding space using the modality-balanced hard negatives; 2) Image verbalization method, which bridges the modality gap between images and texts in the raw data space.
no code implementations • 25 Aug 2022 • Hengyu Liu, Qiang Fu, Lun Du, Tiancheng Zhang, Ge Yu, Shi Han, Dongmei Zhang
Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training.
1 code implementation • 4 May 2022 • Xiaomeng Hu, Shi Yu, Chenyan Xiong, Zhenghao Liu, Zhiyuan Liu, Ge Yu
In this paper, we identify and study the two mismatches between pre-training and ranking fine-tuning: the training schema gap regarding the differences in training objectives and model architectures, and the task knowledge gap considering the discrepancy between the knowledge needed in ranking and that learned during pre-training.
1 code implementation • 25 May 2021 • Tian-Xing Xu, Yuan-Chen Guo, Zhiqiang Li, Ge Yu, Yu-Kun Lai, Song-Hai Zhang
Place recognition plays an essential role in the field of autonomous driving and robot navigation.
Ranked #4 on 3D Place Recognition on CS-Campus3D
no code implementations • 28 Jun 2019 • Ning Wang, Xiaokui Xiao, Yin Yang, Jun Zhao, Siu Cheung Hui, Hyejin Shin, Junbum Shin, Ge Yu
Motivated by this, we first propose novel LDP mechanisms for collecting a numeric attribute, whose accuracy is at least no worse (and usually better) than existing solutions in terms of worst-case noise variance.
3 code implementations • 19 Dec 2014 • Shi Yan, Harumasa Tachibana, Lan-Hai Wei, Ge Yu, Shao-Qing Wen, Chuan-Chao Wang
We therefore conclude that this haplotype is the Y chromosome of the House of Aisin Gioro.
Populations and Evolution
no code implementations • 8 Sep 2014 • Jim Jing-Yan Wang, Xuefeng Cui, Ge Yu, Lili Guo, Xin Gao
In this paper, we try to answer these questions by developing the first joint sparse coding and ranking score learning algorithm.