1 code implementation • 26 Mar 2024 • Jianlin Su, Murtadha Ahmed, Wenbo, Luo Ao, Mingren Zhu, Yunfeng Liu
However, conventional In-Context Learning (ICL) approaches are often impeded by length limitations of transformer architecture, which pose challenges when attempting to effectively integrate supervision from a substantial number of demonstration examples.
1 code implementation • 1 Mar 2024 • Xiangxiang Chu, Jianlin Su, Bo Zhang, Chunhua Shen
Large language models are built on top of a transformer-based architecture to process textual inputs.
4 code implementations • 29 Aug 2023 • Mang Ning, Mingxiao Li, Jianlin Su, Albert Ali Salah, Itir Onal Ertugrul
In this paper, we systematically investigate the exposure bias problem in diffusion models by first analytically modelling the sampling distribution, based on which we then attribute the prediction error at each sampling step as the root cause of the exposure bias issue.
Ranked #9 on Image Generation on CIFAR-10
1 code implementation • 13 Jun 2023 • Ahmed Murtadha, Shengfeng Pan, Wen Bo, Jianlin Su, Xinxin Cao, Wenze Zhang, Yunfeng Liu
To alleviate the noisy information, we adapt a reasoning with uncertainty-based approach to rank the unlabeled texts based on the evidential support received from the labeled texts.
no code implementations • 5 Aug 2022 • Jianlin Su, Mingren Zhu, Ahmed Murtadha, Shengfeng Pan, Bo Wen, Yunfeng Liu
To support the application of deep learning in multi-label classification (MLC) tasks, we propose the ZLPR (zero-bounded log-sum-exp \& pairwise rank-based) loss in this paper.
no code implementations • 5 Aug 2022 • Jianlin Su, Ahmed Murtadha, Shengfeng Pan, Jing Hou, Jun Sun, Wanwei Huang, Bo Wen, Yunfeng Liu
The ultimate goal is to enable a global view that considers the beginning and the end positions to predict the entity.
1 code implementation • 22 Mar 2022 • Murtadha Ahmed, Shengfeng Pan, Jianlin Su, Xinxin Cao, Wenze Zhang, Bo Wen, Yunfeng Liu
Unfortunately, the aspect is often expressed implicitly through a set of representatives and thus renders implicit mapping process unattainable unless sufficient labeled examples are available.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
no code implementations • 23 Dec 2021 • Shaoshi Sun, Zhenyuan Zhang, BoCheng Huang, Pengbin Lei, Jianlin Su, Shengfeng Pan, Jiarun Cao
The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive and sum to one, and the corresponding loss function allows to use maximum likelihood principle to optimize the model.
no code implementations • 10 Oct 2021 • Xiaoxing Wang, Wenxuan Guo, Junchi Yan, Jianlin Su, Xiaokang Yang
Also, we search on the search space of DARTS to compare with peer methods, and our discovered architecture achieves 97. 54% accuracy on CIFAR-10 and 75. 7% top-1 accuracy on ImageNet, which are state-of-the-art performance.
no code implementations • EMNLP (sustainlp) 2021 • Yi Liu, Guoan Zhang, Puning Yu, Jianlin Su, Shengfeng Pan
Copy mechanisms explicitly obtain unchanged tokens from the source (input) sequence to generate the target (output) sequence under the neural seq2seq framework.
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2021 • Rui Li, Shunyi Zheng, Ce Zhang, Chenxi Duan, Jianlin Su, Libo Wang, Peter M. Atkinson
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
Ranked #7 on Semantic Segmentation on ISPRS Vaihingen
1 code implementation • 7 May 2021 • Gongxu Luo, JianXin Li, Jianlin Su, Hao Peng, Carl Yang, Lichao Sun, Philip S. Yu, Lifang He
Based on them, we design MinGE to directly calculate the ideal node embedding dimension for any graph.
18 code implementations • 20 Apr 2021 • Jianlin Su, Yu Lu, Shengfeng Pan, Ahmed Murtadha, Bo Wen, Yunfeng Liu
Then, we propose a novel method named Rotary Position Embedding(RoPE) to effectively leverage the positional information.
Ranked #1 on Semantic Text Matching on CAIL2019-SCM - test
3 code implementations • 29 Mar 2021 • Jianlin Su, Jiarun Cao, Weijie Liu, Yangyiwen Ou
Therefore, some attempts of boosting the isotropy of sentence distribution, such as flow-based model, have been applied to sentence representations and achieved some improvement.
1 code implementation • 29 Nov 2020 • Rui Li, Shunyi Zheng, Chenxi Duan, Jianlin Su, Ce Zhang
The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer vision and natural language processing.
no code implementations • 3 Sep 2020 • Rui Li, Shunyi Zheng, Chenxi Duan, Ce Zhang, Jianlin Su, P. M. Atkinson
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
2 code implementations • 29 Jul 2020 • Rui Li, Jianlin Su, Chenxi Duan, Shunyi Zheng
In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs.
1 code implementation • ACL 2020 • Qile Zhu, Jianlin Su, Wei Bi, Xiaojiang Liu, Xiyao Ma, Xiaolin Li, Dapeng Wu
Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks.
5 code implementations • ACL 2020 • Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang
Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction.
Ranked #5 on Relation Extraction on NYT11-HRL
2 code implementations • 5 Mar 2019 • Jianlin Su
We decompose the network of discriminator orthogonally and add an extra loss into the objective of common GANs, which can enforce discriminator become an effective encoder.
1 code implementation • 14 Feb 2019 • Rahul Bhalley, Jianlin Su
In this paper we address the problem of artist style transfer where the painting style of a given artist is applied on a real world photograph.
1 code implementation • 29 Jan 2019 • Hao Ren, Jianlin Su, Hong Lu
In this paper, we propose a new image classification task called Top-2 classification to evaluate the generalization ability of CNNs and CapsNets.
5 code implementations • 18 Nov 2018 • Jianlin Su
A significant improvement is WGAN, with the help of 1-Lipschitz constraint on discriminator to prevent from gradient vanishing.
2 code implementations • 25 Oct 2018 • Jianlin Su
In this article, we introduce a new mode for training Generative Adversarial Networks (GANs).
1 code implementation • 16 Sep 2018 • Jianlin Su, Guang Wu
In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs.
no code implementations • 16 Jul 2018 • Jianlin Su
We reinterpreting the variational inference in a new perspective.