Search Results for author: Qing Yang

Found 47 papers, 16 papers with code

Meaningful Learning: Advancing Abstract Reasoning in Large Language Models via Generic Fact Guidance

no code implementations14 Mar 2024 Kai Xiong, Xiao Ding, Ting Liu, Bing Qin, Dongliang Xu, Qing Yang, Hongtao Liu, Yixin Cao

Large language models (LLMs) have developed impressive performance and strong explainability across various reasoning scenarios, marking a significant stride towards mimicking human-like intelligence.

Memorization

Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models

no code implementations1 Mar 2024 Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Xu Wang, Qing Yang, Dongliang Xu, Wanxiang Che

Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated).

Program Synthesis

MultiPoT: Multilingual Program of Thoughts Harnesses Multiple Programming Languages

no code implementations16 Feb 2024 Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Libo Qin, Xu Wang, Qing Yang, Dongliang Xu, Wanxiang Che

In this paper, we conduct comprehensive experiments on the programming languages used in PoT and find that no single language consistently delivers optimal performance across all tasks and models.

StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models

no code implementations25 Jan 2024 Yalong Bai, Mohan Zhou, Qing Yang

The ability to fine-tune generative models for text-to-image generation tasks is crucial, particularly facing the complexity involved in accurately interpreting and visualizing textual inputs.

Language Modelling Text-to-Image Generation +1

SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models

no code implementations16 Jan 2024 Weixiang Zhao, Shilong Wang, Yulin Hu, Yanyan Zhao, Bing Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che

Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input, aiming at handling the challenges of catastrophic forgetting and knowledge transfer in CL.

Continual Learning Transfer Learning

VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detection

no code implementations26 Dec 2023 Sudip Dhakal, Dominic Carrillo, Deyuan Qu, Michael Nutt, Qing Yang, Song Fu

In recent times, there has been a notable surge in multimodal approaches that decorates raw LiDAR point clouds with camera-derived features to improve object detection performance.

2D Semantic Segmentation 3D Object Detection +3

Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction

no code implementations16 Dec 2023 Zhaoxi Mu, Xinyu Yang, Sining Sun, Qing Yang

However, in the task of target speech extraction, certain elements of global and local semantic information in the reference speech, which are irrelevant to speaker identity, can lead to speaker confusion within the speech extraction network.

Disentanglement Speech Extraction

SiCP: Simultaneous Individual and Cooperative Perception for 3D Object Detection in Connected and Automated Vehicles

1 code implementation8 Dec 2023 Deyuan Qu, Qi Chen, Tianyu Bai, Andy Qin, HongSheng Lu, Heng Fan, Song Fu, Qing Yang

Cooperative perception for connected and automated vehicles is traditionally achieved through the fusion of feature maps from two or more vehicles.

3D Object Detection object-detection

Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning

1 code implementation1 Dec 2023 Shaohua Dong, Yunhe Feng, Qing Yang, Yan Huang, Dongfang Liu, Heng Fan

Existing approaches often fully fine-tune a dual-branch encoder-decoder framework with a complicated feature fusion strategy for achieving multimodal semantic segmentation, which is training-costly due to the massive parameter updates in feature extraction and fusion.

object-detection Object Detection +6

Key Frame Mechanism For Efficient Conformer Based End-to-end Speech Recognition

1 code implementation23 Oct 2023 Peng Fan, Changhao Shan, Sining Sun, Qing Yang, Jianwei Zhang

Following the initial encoder, we introduce an intermediate CTC loss function to compute the label frame, enabling us to extract the key frames and blank frames for KFSA.

Automatic Speech Recognition speech-recognition +1

UAV-assisted Semantic Communication with Hybrid Action Reinforcement Learning

no code implementations18 Aug 2023 Peiyuan Si, Jun Zhao, Kwok-Yan Lam, Qing Yang

In this paper, we aim to explore the use of uplink semantic communications with the assistance of UAV in order to improve data collection effiicency for metaverse users in remote areas.

reinforcement-learning Reinforcement Learning (RL)

Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline

no code implementations19 Jul 2023 Zhigang Chang, Weitai Hu, Qing Yang, Shibao Zheng

In dyadic speaker-listener interactions, the listener's head reactions along with the speaker's head movements, constitute an important non-verbal semantic expression together.

Talking Head Generation Video Generation

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models

no code implementations24 May 2023 Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.

Data Augmentation

CGCE: A Chinese Generative Chat Evaluation Benchmark for General and Financial Domains

1 code implementation23 May 2023 Xuanyu Zhang, Bingbing Li, Qing Yang

Generative chat models, such as ChatGPT and GPT-4, have revolutionized natural language generation (NLG) by incorporating instructions and human feedback to achieve significant performance improvements.

Text Generation

XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters

1 code implementation19 May 2023 Xuanyu Zhang, Qing Yang, Dongliang Xu

In recent years, pre-trained language models have undergone rapid development with the emergence of large-scale models.

Self-QA: Unsupervised Knowledge Guided Language Model Alignment

1 code implementation19 May 2023 Xuanyu Zhang, Qing Yang

Large-scale language models like ChatGPT and GPT-4 have gained attention for their impressive conversational and generative capabilities.

Language Modelling Question Answering

Towards Causal Representation Learning and Deconfounding from Indefinite Data

no code implementations4 May 2023 Hang Chen, Xinyu Yang, Qing Yang

We implement the above designs as a dynamic variational inference model, tailored to learn causal representation from indefinite data under latent confounding.

Causal Discovery Disentanglement +1

PUNR: Pre-training with User Behavior Modeling for News Recommendation

1 code implementation25 Apr 2023 Guangyuan Ma, Hongtao Liu, Xing Wu, Wanhui Qian, Zhepeng Lv, Qing Yang, Songlin Hu

Firstly, we introduce the user behavior masking pre-training task to recover the masked user behaviors based on their contextual behaviors.

News Recommendation Unsupervised Pre-training

UAV aided Metaverse over Wireless Communications: A Reinforcement Learning Approach

no code implementations4 Jan 2023 Peiyuan Si, Wenhan Yu, Jun Zhao, Kwok-Yan Lam, Qing Yang

A huge amount of data in physical world needs to be synchronized to the virtual world to provide immersive experience for users, and there will be higher requirements on coverage to include more users into Metaverse.

reinforcement-learning Reinforcement Learning (RL)

An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning

no code implementations30 Nov 2022 Shaohuai Shi, Qing Yang, Yang Xiang, Shuhan Qi, Xuan Wang

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning.

Improve Ranking Correlation of Super-net through Training Scheme from One-shot NAS to Few-shot NAS

1 code implementation13 Jun 2022 Jiawei Liu, Kaiyu Zhang, Weitai Hu, Qing Yang

To address this problem, we propose a step-by-step training super-net scheme from one-shot NAS to few-shot NAS.

Neural Architecture Search

An Empirical Study on Disentanglement of Negative-free Contrastive Learning

1 code implementation9 Jun 2022 Jinkun Cao, Ruiqian Nai, Qing Yang, Jialei Huang, Yang Gao

In this paper, we examine negative-free contrastive learning methods to study the disentanglement property empirically.

Contrastive Learning Disentanglement

Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks

1 code implementation1 Feb 2022 Yu Zhao, Shaopeng Wei, Yu Guo, Qing Yang, Xingyan Chen, Qing Li, Fuzhen Zhuang, Ji Liu, Gang Kou

This study for the first time considers both types of risk and their joint effects in bankruptcy prediction.

Online Self-Evolving Anomaly Detection in Cloud Computing Environments

1 code implementation16 Nov 2021 Haili Wang, Jingda Guo, Xu Ma, Song Fu, Qing Yang, Yunzhong Xu

As a distinct advantage of our framework, cloud system administrators only need to check a small number of detected anomalies, and their decisions are leveraged to update the detector.

Anomaly Detection Cloud Computing +2

Revisit Dictionary Learning for Video Compressive Sensing under the Plug-and-Play Framework

no code implementations11 Oct 2021 Qing Yang, Yaping Zhao

Aiming at high-dimensional (HD) data acquisition and analysis, snapshot compressive imaging (SCI) obtains the 2D compressed measurement of HD data with optical imaging systems and reconstructs HD data using compressive sensing algorithms.

Compressive Sensing Denoising +3

Disentangling Properties of Contrastive Methods

no code implementations29 Sep 2021 Jinkun Cao, Qing Yang, Jialei Huang, Yang Gao

In this paper, we explored the possibility of using contrastive methods to learn a disentangled representation, a discriminative approach that is drastically different from previous approaches.

Disentanglement Object Recognition

IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction via Implicit Neural Representation

no code implementations29 Jun 2021 Qing Wu, Yuwei Li, Lan Xu, Ruiming Feng, Hongjiang Wei, Qing Yang, Boliang Yu, Xiaozhao Liu, Jingyi Yu, Yuyao Zhang

For collecting high-quality high-resolution (HR) MR image, we propose a novel image reconstruction network named IREM, which is trained on multiple low-resolution (LR) MR images and achieve an arbitrary up-sampling rate for HR image reconstruction.

Anatomy Image Reconstruction +1

Distributed Energy Trading Management for Renewable Prosumers with HVAC and Energy Storage

no code implementations1 May 2021 Qing Yang, Hao Wang

This work develops a novel distributed method for the residential transactive energy system that enables multiple users to interactively optimize their energy management of HVAC systems and behind-the-meter batteries.

Distributed Optimization energy trading +1

Blockchain-Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant

no code implementations1 May 2021 Qing Yang, Hao Wang, Taotao Wang, Shengli Zhang, Xiaoxiao Wu, Hui Wang

In this paper, we develop a blockchain-based VPP energy management platform to facilitate a rich set of transactive energy activities among residential users with renewables, energy storage, and flexible loads in a VPP.

energy trading Management +1

Privacy-Preserving Transactive Energy Management for IoT-aided Smart Homes via Blockchain

no code implementations11 Jan 2021 Qing Yang, Hao Wang

Further, we design an efficient blockchain system tailored for IoT devices and develop the smart contract to support the holistic transactive energy management system.

energy trading Management +1

Asset Allocation via Machine Learning and Applications to Equity Portfolio Management

no code implementations1 Nov 2020 Qing Yang, Zhenning Hong, Ruyan Tian, Tingting Ye, Liangliang Zhang

In this paper, we document a novel machine learning based bottom-up approach for static and dynamic portfolio optimization on, potentially, a large number of assets.

BIG-bench Machine Learning Management +1

Cooperative Energy Management of HVAC via Transactive Energy

no code implementations26 Oct 2020 Qing Yang, Hao Wang

However, how to scale up HVAC energy management for a group of users while persevering users' privacy remains a big challenge.

energy trading Management +1

CoFF: Cooperative Spatial Feature Fusion for 3D Object Detection on Autonomous Vehicles

no code implementations24 Sep 2020 Jingda Guo, Dominic Carrillo, Sihai Tang, Qi Chen, Qing Yang, Song Fu, Xi Wang, Nannan Wang, Paparao Palacharla

To reduce the amount of transmitted data, feature map based fusion is recently proposed as a practical solution to cooperative 3D object detection by autonomous vehicles.

3D Object Detection Autonomous Vehicles +2

DCANet: Learning Connected Attentions for Convolutional Neural Networks

no code implementations9 Jul 2020 Xu Ma, Jingda Guo, Sihai Tang, Zhinan Qiao, Qi Chen, Qing Yang, Song Fu

With DCANet, all attention blocks in a CNN model are trained jointly, which improves the ability of attention learning.

MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations

1 code implementation4 Jun 2020 Qing Yang, Xia Zhu, Jong-Kae Fwu, Yun Ye, Ganmei You, Yuan Zhu

Deep neural networks (DNNs) have recently been applied and used in many advanced and diverse tasks, such as medical diagnosis, automatic driving, etc.

Medical Diagnosis

PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing

1 code implementation24 Apr 2020 Qing Yang, Xia Zhu, Jong-Kae Fwu, Yun Ye, Ganmei You, Yuan Zhu

Face anti-spoofing has become an increasingly important and critical security feature for authentication systems, due to rampant and easily launchable presentation attacks.

Face Anti-Spoofing General Classification +1

Channel Pruning via Optimal Thresholding

1 code implementation10 Mar 2020 Yun Ye, Ganmei You, Jong-Kae Fwu, Xia Zhu, Qing Yang, Yuan Zhu

By using OT, most negligible or unimportant channels are pruned to achieve high sparsity while minimizing performance degradation.

DASNet: Dynamic Activation Sparsity for Neural Network Efficiency Improvement

no code implementations13 Sep 2019 Qing Yang, Jiachen Mao, Zuoguan Wang, Hai Li

In addition to conventional compression techniques, e. g., weight pruning and quantization, removing unimportant activations can reduce the amount of data communication and the computation cost.

Quantization

Joint Regularization on Activations and Weights for Efficient Neural Network Pruning

no code implementations19 Jun 2019 Qing Yang, Wei Wen, Zuoguan Wang, Hai Li

With the rapid scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for improving deployment efficiency.

Efficient Neural Network Model Compression +1

Integral Pruning on Activations and Weights for Efficient Neural Networks

no code implementations ICLR 2019 Qing Yang, Wei Wen, Zuoguan Wang, Yiran Chen, Hai Li

With the rapidly scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for efficient deployment.

Model Compression

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