Search Results for author: Tianyi Yan

Found 10 papers, 3 papers with code

Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers

2 code implementations5 Sep 2019 Yukuan Yang, Shuang Wu, Lei Deng, Tianyi Yan, Yuan Xie, Guoqi Li

In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency.

Quantization

Robust Natural Language Understanding with Residual Attention Debiasing

1 code implementation28 May 2023 Fei Wang, James Y. Huang, Tianyi Yan, Wenxuan Zhou, Muhao Chen

However, previous ensemble-based debiasing methods typically apply debiasing on top-level logits without directly addressing biased attention patterns.

Natural Language Understanding

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

no code implementations21 Aug 2020 Dingheng Wang, Bijiao Wu, Guangshe Zhao, Man Yao, Hengnu Chen, Lei Deng, Tianyi Yan, Guoqi Li

Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition.

Tensor Decomposition Video Recognition

Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization

no code implementations27 May 2021 Yukuan Yang, Xiaowei Chi, Lei Deng, Tianyi Yan, Feng Gao, Guoqi Li

In summary, the EOQ framework is specially designed for reducing the high cost of convolution and BN in network training, demonstrating a broad application prospect of online training in resource-limited devices.

Model Compression Quantization

Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification

no code implementations14 Jun 2022 Tianyi Yan, Kuan Zhu, Haiyun Guo, Guibo Zhu, Ming Tang, Jinqiao Wang

Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identification (Re-ID).

Clustering Pseudo Label +1

Connectional-Style-Guided Contextual Representation Learning for Brain Disease Diagnosis

no code implementations8 Jun 2023 Gongshu Wang, Ning Jiang, Yunxiao Ma, Tiantian Liu, Duanduan Chen, Jinglong Wu, Guoqi Li, Dong Liang, Tianyi Yan

In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis.

Representation Learning

Multi-task Collaborative Pre-training and Individual-adaptive-tokens Fine-tuning: A Unified Framework for Brain Representation Learning

no code implementations20 Jun 2023 Ning Jiang, Gongshu Wang, Tianyi Yan

Structural magnetic resonance imaging (sMRI) provides accurate estimates of the brain's structural organization and learning invariant brain representations from sMRI is an enduring issue in neuroscience.

Anatomy Attribute +2

Contrastive Instruction Tuning

no code implementations17 Feb 2024 Tianyi Yan, Fei Wang, James Y. Huang, Wenxuan Zhou, Fan Yin, Aram Galstyan, Wenpeng Yin, Muhao Chen

Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks.

Sentence

Monotonic Paraphrasing Improves Generalization of Language Model Prompting

no code implementations24 Mar 2024 Qin Liu, Fei Wang, Nan Xu, Tianyi Yan, Tao Meng, Muhao Chen

In this paper, we propose monotonic paraphrasing (MonoPara), an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt (or instruction) rewriting, and a target LM (i. e. the prompt or instruction executor) that constrains the generation for lower perplexity.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.