1 code implementation • 1 Apr 2024 • Fengtao Zhou, Yingxue Xu, Yanfen Cui, Shenyan Zhang, Yun Zhu, Weiyang He, Jiguang Wang, Xin Wang, Ronald Chan, Louis Ho Shing Lau, Chu Han, Dafu Zhang, Zhenhui Li, Hao Chen
The limited availability of modalities for each patient would cause information loss, adversely affecting predictive accuracy.
no code implementations • 27 Feb 2024 • Chu-Cheng Lin, Xinyi Wang, Jonathan H. Clark, Han Lu, Yun Zhu, Chenxi Whitehouse, Hongkun Yu
By composing feature-specific parameters for each dataset, FLix can accommodate diverse dataset mixtures and generalize better to unseen datasets.
1 code implementation • 29 Jan 2024 • Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, Zhen-Hua Ling
Experiments on four datasets covering short- and long-form generation tasks show that CRAG can significantly improve the performance of RAG-based approaches.
no code implementations • 28 Jan 2024 • Yun Zhu, Yaoke Wang, Haizhou Shi, Siliang Tang
In this paper, we propose ENGINE, a parameter- and memory-efficient fine-tuning method for textual graphs with an LLM encoder.
no code implementations • 14 Jan 2024 • Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng
We investigate this approach under two different settings: one where the policy model is smaller and is paired with a more powerful critic model, and another where a single language model fulfills both roles.
1 code implementation • 21 Dec 2023 • Yun Zhu, Le Hui, Yaqi Shen, Jin Xie
To this end, we propose a novel superpoint grouping network for indoor anchor-free one-stage 3D object detection.
Ranked #4 on 3D Object Detection on S3DIS
no code implementations • 15 Nov 2023 • Yun Zhu, Nevan Wichers, Chu-Cheng Lin, Xinyi Wang, Tianlong Chen, Lei Shu, Han Lu, Canoee Liu, Liangchen Luo, Jindong Chen, Lei Meng
Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks.
no code implementations • 15 Nov 2023 • Lei Shu, Nevan Wichers, Liangchen Luo, Yun Zhu, Yinxiao Liu, Jindong Chen, Lei Meng
Evaluating natural language systems poses significant challenges, particularly in the realms of natural language understanding and high-level reasoning.
1 code implementation • 25 Oct 2023 • Bowen Tan, Yun Zhu, Lijuan Liu, Hongyi Wang, Yonghao Zhuang, Jindong Chen, Eric Xing, Zhiting Hu
In this work, we present RedCoast(Redco), a lightweight and user-friendly tool crafted to automate distributed training and inference for LLMs, as well as to simplify ML pipeline development.
no code implementations • 11 Oct 2023 • Yun Zhu, Yaoke Wang, Haizhou Shi, Zhenshuo Zhang, Dian Jiao, Siliang Tang
These pre-trained models can be applied to various downstream Web applications, saving training time and improving downstream (target) performance.
no code implementations • 7 Oct 2023 • Liangchen Luo, Zi Lin, Yinxiao Liu, Lei Shu, Yun Zhu, Jingbo Shang, Lei Meng
In the era of large language models (LLMs), this study explores the ability of LLMs to deliver accurate critiques across various tasks.
no code implementations • 25 Sep 2023 • Duleep Rathgamage Don, Ying Xie, Le Yu, Simon Hughes, Yun Zhu
This paper proposes a novel method to improve the accuracy of product search in e-commerce by utilizing a cluster language model.
no code implementations • 22 Aug 2023 • Yun Zhu, Yinxiao Liu, Felix Stahlberg, Shankar Kumar, Yu-Hui Chen, Liangchen Luo, Lei Shu, Renjie Liu, Jindong Chen, Lei Meng
Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting.
1 code implementation • 24 Jul 2023 • Yun Zhu, Haizhou Shi, Zhenshuo Zhang, Siliang Tang
In this work, we investigate the problem of out-of-distribution (OOD) generalization for unsupervised learning methods on graph data.
no code implementations • 25 May 2023 • Yun Zhu, Kangkang Zhang, Yuncai Zhu, Jinming Zhou
Most MPC (Model Predictive Control) algorithms used in industries and studied in the control academia use a two-term QP (quadratic programming), where the first term is the weighted norm of the output errors, and the second term is that of the input increments.
1 code implementation • 25 May 2023 • Lei Shu, Liangchen Luo, Jayakumar Hoskere, Yun Zhu, Yinxiao Liu, Simon Tong, Jindong Chen, Lei Meng
In this work, we develop new strategies for instruction tuning and reinforcement learning to better align LLMs for cross-sentence rewriting tasks using diverse wording and structures expressed through natural languages including 1) generating rewriting instruction data from Wiki edits and public corpus through instruction generation and chain-of-thought prompting; 2) collecting comparison data for reward model training through a new ranking function.
no code implementations • 16 Mar 2023 • Boren Hu, Yun Zhu, Jiacheng Li, Siliang Tang
In this paper, we propose a novel dynamic early exiting combined with layer skipping for BERT inference named SmartBERT, which adds a skipping gate and an exiting operator into each layer of BERT.
no code implementations • 9 Mar 2023 • Zhenshuo Zhang, Yun Zhu, Haizhou Shi, Siliang Tang
Albeit having gained significant progress lately, large-scale graph representation learning remains expensive to train and deploy for two main reasons: (i) the repetitive computation of multi-hop message passing and non-linearity in graph neural networks (GNNs); (ii) the computational cost of complex pairwise contrastive learning loss.
no code implementations • 24 Feb 2023 • Yun Zhu, Jianhao Guo, Siliang Tang
And aiming for graph classification task, we unify pre-training and fine-tuning by designing a novel verbalizer-free prompting function, which reformulates the downstream task in a similar format as pretext task.
1 code implementation • 29 Apr 2022 • Yun Zhu, Jianhao Guo, Fei Wu, Siliang Tang
To the best of our awareness, RoSA is the first work focuses on the non-aligned node-node graph contrastive learning problem.
no code implementations • 28 Dec 2021 • Fang-Qi Li, Shi-Lin Wang, Yun Zhu
The wide application of deep learning techniques is boosting the regulation of deep learning models, especially deep neural networks (DNN), as commercial products.
no code implementations • 3 Nov 2020 • Yun Zhu
To address this problem, we present an efficient information-theoretic approach to manage the sensors for better tracking of the unknown and time-varying number of targets.
no code implementations • 19 Sep 2020 • Yun Zhu, Sayyed M. Zahiri, Jiaqi Wang, Han-Yu Chen, Faizan Javed
Entity-based semantic search has been widely adopted in modern search engines to improve search accuracy by understanding users' intent.
no code implementations • 11 Jun 2020 • Xiang-Wei Feng, Da-Zheng Feng, Yun Zhu
After iteration begins, our method only needs to update a diagonal matrix with linear computational complexity, and perform matrix multiplication operation with time complexity approximately O(M2) in each iteration.
no code implementations • 20 Sep 2016 • Yun Zhu, Faizan Javed, Ozgur Ozturk
A large-scale job title classification system can power various downstream applications such as semantic search, job recommendations and labor market analytics.