Search Results for author: Xiaoyang Li

Found 15 papers, 6 papers with code

decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points

1 code implementation19 Apr 2024 Yi Guo, Fanliu Kong, Xiaoyang Li, Hui Li, Wei Chen, Xiaogang Tian, Jinping Cai, Yang Zhang, Shouda Liu

However, existing quantization schemes suffer from significant accuracy degradation at very low bits, or require some additional computational overhead when deployed, making it difficult to be applied to large-scale applications in industry.


RadioGAT: A Joint Model-based and Data-driven Framework for Multi-band Radiomap Reconstruction via Graph Attention Networks

no code implementations25 Mar 2024 Xiaojie Li, Songyang Zhang, Hang Li, Xiaoyang Li, Lexi Xu, Haigao Xu, Hui Mei, Guangxu Zhu, Nan Qi, Ming Xiao

Multi-band radiomap reconstruction (MB-RMR) is a key component in wireless communications for tasks such as spectrum management and network planning.

Graph Attention

Finding the Missing Data: A BERT-inspired Approach Against Package Loss in Wireless Sensing

1 code implementation19 Mar 2024 Zijian Zhao, TingWei Chen, Fanyi Meng, Hang Li, Xiaoyang Li, Guangxu Zhu

Despite the development of various deep learning methods for Wi-Fi sensing, package loss often results in noncontinuous estimation of the Channel State Information (CSI), which negatively impacts the performance of the learning models.

Action Classification Person Identification

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

1 code implementation8 Feb 2024 Haotong Qin, Xudong Ma, Xingyu Zheng, Xiaoyang Li, Yang Zhang, Shouda Liu, Jie Luo, Xianglong Liu, Michele Magno

This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention.


RdimKD: Generic Distillation Paradigm by Dimensionality Reduction

no code implementations14 Dec 2023 Yi Guo, Yiqian He, Xiaoyang Li, Haotong Qin, Van Tung Pham, Yang Zhang, Shouda Liu

Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices.

Dimensionality Reduction Knowledge Distillation

Integrated Sensing-Communication-Computation for Edge Artificial Intelligence

no code implementations1 Jun 2023 Dingzhu Wen, Xiaoyang Li, Yong Zhou, Yuanming Shi, Sheng Wu, Chunxiao Jiang

Edge artificial intelligence (AI) has been a promising solution towards 6G to empower a series of advanced techniques such as digital twins, holographic projection, semantic communications, and auto-driving, for achieving intelligence of everything.

BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance

1 code implementation13 Nov 2022 Haotong Qin, Xudong Ma, Yifu Ding, Xiaoyang Li, Yang Zhang, Zejun Ma, Jiakai Wang, Jie Luo, Xianglong Liu

We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25. 1x speedup and 20. 2x storage-saving on edge hardware.

Binarization Keyword Spotting

BiFSMN: Binary Neural Network for Keyword Spotting

1 code implementation14 Feb 2022 Haotong Qin, Xudong Ma, Yifu Ding, Xiaoyang Li, Yang Zhang, Yao Tian, Zejun Ma, Jie Luo, Xianglong Liu

Then, to allow the instant and adaptive accuracy-efficiency trade-offs at runtime, we also propose a Thinnable Binarization Architecture to further liberate the acceleration potential of the binarized network from the topology perspective.

Binarization Keyword Spotting

Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification

no code implementations9 Jul 2020 Pengyu Yuan, Aryan Mobiny, Jahandar Jahanipour, Xiaoyang Li, Pietro Antonio Cicalese, Badrinath Roysam, Vishal Patel, Maric Dragan, Hien Van Nguyen

Meta-learning aims to deliver an adaptive model that is sensitive to these underlying distribution changes, but requires many tasks during the meta-training process.

Active Learning General Classification +1

An Overview of Data-Importance Aware Radio Resource Management for Edge Machine Learning

no code implementations10 Nov 2019 Dingzhu Wen, Xiaoyang Li, Qunsong Zeng, Jinke Ren, Kaibin Huang

Specifically, the metrics that measure data importance in active learning (e. g., classification uncertainty and data diversity) are applied to RRM for efficient acquisition of distributed data in wireless networks to train AI models at servers.

Active Learning BIG-bench Machine Learning +2

Attenuating Random Noise in Seismic Data by a Deep Learning Approach

no code implementations28 Oct 2019 Xing Zhao, Ping Lu, Yanyan Zhang, Jianxiong Chen, Xiaoyang Li

In the geophysical field, seismic noise attenuation has been considered as a critical and long-standing problem, especially for the pre-stack data processing.

Regulatory Focus: Promotion and Prevention Inclinations in Policy Search

no code implementations25 Sep 2019 Lanxin Lei, Zhizhong Li, Xiaoyang Li, Cong Qiu, Dahua Lin

The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths.

Atari Games Continuous Control +1

RISAS: A Novel Rotation, Illumination, Scale Invariant Appearance and Shape Feature

no code implementations14 Mar 2016 Kanzhi Wu, Xiaoyang Li, Ravindra Ranasinghe, Gamini Dissanayake, Yong liu

This paper presents a novel appearance and shape feature, RISAS, which is robust to viewpoint, illumination, scale and rotation variations.

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