Search Results for author: Chenyang Li

Found 24 papers, 9 papers with code

Invisible Needle Detection in Ultrasound: Leveraging Mechanism-Induced Vibration

no code implementations21 Mar 2024 Chenyang Li, Dianye Huang, Angelos Karlas, Nassir Navab, Zhongliang Jiang

In clinical applications that involve ultrasound-guided intervention, the visibility of the needle can be severely impeded due to steep insertion and strong distractors such as speckle noise and anatomical occlusion.

Fourier Circuits in Neural Networks: Unlocking the Potential of Large Language Models in Mathematical Reasoning and Modular Arithmetic

no code implementations12 Feb 2024 Jiuxiang Gu, Chenyang Li, YIngyu Liang, Zhenmei Shi, Zhao Song, Tianyi Zhou

Our research presents a thorough analytical characterization of the features learned by stylized one-hidden layer neural networks and one-layer Transformers in addressing this task.

Mathematical Reasoning

WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope

no code implementations3 Jan 2024 Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Yusen Hu, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Bin Luo, Yifeng Geng, Xuansong Xie, Jingren Zhou

This paper introduces the WordArt Designer API, a novel framework for user-driven artistic typography synthesis utilizing Large Language Models (LLMs) on ModelScope.

One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space

no code implementations24 Nov 2023 Raghav Addanki, Chenyang Li, Zhao Song, Chiwun Yang

Considering a single-layer self-attention with Query, Key, and Value matrices $Q, K, V \in \mathbb{R}^{n \times d}$, the polynomial method approximates the attention output $T \in \mathbb{R}^{n \times d}$.

Attribute

A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer

no code implementations22 Nov 2023 Chenyang Li, Zhao Song, Weixin Wang, Chiwun Yang

The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients.

Privacy Preserving

Implementing a new fully stepwise decomposition-based sampling technique for the hybrid water level forecasting model in real-world application

no code implementations19 Sep 2023 Ziqian Zhang, Nana Bao, Xingting Yan, Aokai Zhu, Chenyang Li, MingYu Liu

Results of VMD-based hybrid model using FSDB sampling technique show that Nash-Sutcliffe Efficiency (NSE) coefficient is increased by 6. 4%, 28. 8% and 7. 0% in three stations respectively, compared with those obtained from the currently most advanced sampling technique.

Time Series Time Series Forecasting

Real-time frequency measurement based on parallel pipeline FFT for time-stretched acquisition system

no code implementations18 Aug 2023 Ruiyuan Ming, Peng Ye, Kuojun Yang, Zhixiang Pan, Chenyang Li, Chuang Huang

Real-time frequency measurement for non-repetitive and statistically rare signals are challenging problems in the electronic measurement area, which places high demands on the bandwidth, sampling rate, data processing and transmission capabilities of the measurement system.

Tracking Anything in High Quality

1 code implementation26 Jul 2023 Jiawen Zhu, Zhenyu Chen, Zeqi Hao, Shijie Chang, Lu Zhang, Dong Wang, Huchuan Lu, Bin Luo, Jun-Yan He, Jin-Peng Lan, Hanyuan Chen, Chenyang Li

To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results.

Object Semantic Segmentation +3

Thoracic Cartilage Ultrasound-CT Registration using Dense Skeleton Graph

1 code implementation7 Jul 2023 Zhongliang Jiang, Chenyang Li, Xuesong Li, Nassir Navab

To address this challenge, a graph-based non-rigid registration is proposed to enable transferring planned paths from the atlas to the current setup by explicitly considering subcutaneous bone surface features instead of the skin surface.

Template Matching

DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving

1 code implementation30 Mar 2023 Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Wangmeng Xiang, Binghui Chen, Bin Luo, Yifeng Geng, Xuansong Xie

Real-time perception, or streaming perception, is a crucial aspect of autonomous driving that has yet to be thoroughly explored in existing research.

Autonomous Driving

On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee

1 code implementation13 Mar 2023 Chenyang Li, Jihoon Chung, Biao Cai, Haimin Wang, Xianlian Zhou, Bo Shen

This paper focuses on two model compression techniques: low-rank approximation and weight pruning in neural networks, which are very popular nowadays.

Image Classification Model Compression +1

LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception

2 code implementations27 Oct 2022 Chenyang Li, Zhi-Qi Cheng, Jun-Yan He, Pengyu Li, Bin Luo, Hanyuan Chen, Yifeng Geng, Jin-Peng Lan, Xuansong Xie

Streaming perception is a critical task in autonomous driving that requires balancing the latency and accuracy of the autopilot system.

Autonomous Driving

Unsupervised Industrial Anomaly Detection via Pattern Generative and Contrastive Networks

no code implementations20 Jul 2022 Jianfeng Huang, Chenyang Li, Yimin Lin, Shiguo Lian

After this, we use the Siamese-based network to compute the similarity of the generation image patch and original image patch.

Unsupervised Anomaly Detection

Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages

no code implementations2 Oct 2021 Chenyang Li, Gongxu Luo

Although the multilingual Neural Machine Translation(NMT), which extends Google's multilingual NMT, has ability to perform zero-shot translation and the iterative self-learning algorithm can improve the quality of zero-shot translation, it confronts with two problems: the multilingual NMT model is prone to generate wrong target language when implementing zero-shot translation; the self-learning algorithm, which uses beam search to generate synthetic parallel data, demolishes the diversity of the generated source language and amplifies the impact of the same noise during the iterative learning process.

Machine Translation NMT +3

Pretrain-Finetune Based Training of Task-Oriented Dialogue Systems in a Real-World Setting

no code implementations NAACL 2021 Manisha Srivastava, Yichao Lu, Riley Peschon, Chenyang Li

In this work, we present a method for training retrieval-based dialogue systems using a small amount of high-quality, annotated data and a larger, unlabeled dataset.

Retrieval Task-Oriented Dialogue Systems

Collaborative Adversarial Learning for RelationalLearning on Multiple Bipartite Graphs

no code implementations16 Jul 2020 Jingchao Su, Xu Chen, Ya zhang, Siheng Chen, Dan Lv, Chenyang Li

The two-level alignment acts as two different constraints on different relations of the shared entities and facilitates better knowledge transfer for relational learning on multiple bipartite graphs.

Relational Reasoning Transfer Learning

Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module

1 code implementation17 Nov 2018 Chenyang Li, Xin Zhang, Lufan Liao, Lianwen Jin, Weixin Yang

In this paper, we first leverage a robust feature descriptor, path signature (PS), and propose three PS features to explicitly represent the spatial and temporal motion characteristics, i. e., spatial PS (S_PS), temporal PS (T_PS) and temporal spatial PS (T_S_PS).

Computational Efficiency General Classification +1

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