Search Results for author: Zhou Yang

Found 30 papers, 8 papers with code

Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?

no code implementations27 Jan 2025 Yunbo Lyu, Zhou Yang, Yuqing Niu, Jing Jiang, David Lo

We evaluate seven gender bias detectors and find that none fully capture the actual level of bias in T2I models, with some detectors overestimating bias by up to 26. 95%.

Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory

no code implementations2 Jan 2025 Zhou Yang, Zhengyu Qi, Zhaochun Ren, Zhikai Jia, Haizhou Sun, Xiaofei Zhu, Xiangwen Liao

We propose a non-training construction strategy to define a task space and identify the following key findings: (1) LLMs compress input information into specific task spaces (e. g., sentiment space, topic space) to facilitate task understanding; (2) they then extract and utilize relevant information from the task space at critical moments to generate accurate predictions.

Bias in Large Language Models: Origin, Evaluation, and Mitigation

no code implementations16 Nov 2024 Yufei Guo, Muzhe Guo, Juntao Su, Zhou Yang, Mengqiu Zhu, Hongfei Li, Mengyang Qiu, Shuo Shuo Liu

This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies.

Bias Detection

A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion

1 code implementation14 Jun 2024 Kailai Sun, Zhou Yang, Qianchuan Zhao

Compared to the existing methods, our proposed network, achieves the state-of-the-art performance on the Matterport3D dataset.

3D Reconstruction Autonomous Driving +4

E-ICL: Enhancing Fine-Grained Emotion Recognition through the Lens of Prototype Theory

no code implementations4 Jun 2024 Zhaochun Ren, Zhou Yang, Chenglong Ye, Yufeng Wang, Haizhou Sun, Chao Chen, Xiaofei Zhu, Yunbing Wu, Xiangwen Liao

Specifically, we conduct extensive pilot experiments and find that ICL conforms to the prototype theory on fine-grained emotion recognition.

Emotion Recognition In-Context Learning

AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation

1 code implementation25 Apr 2024 Zhensu Sun, Xiaoning Du, Zhou Yang, Li Li, David Lo

To improve inference efficiency and reduce computational costs, we propose the concept of AI-oriented grammar.

Code Generation Math

An Iterative Associative Memory Model for Empathetic Response Generation

1 code implementation28 Feb 2024 Zhou Yang, Zhaochun Ren, Yufeng Wang, Chao Chen, Haizhou Sun, Xiaofei Zhu, Xiangwen Liao

Empathetic response generation aims to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses.

Empathetic Response Generation Response Generation

Exploiting Emotion-Semantic Correlations for Empathetic Response Generation

1 code implementation27 Feb 2024 Zhou Yang, Zhaochun Ren, Yufeng Wang, Xiaofei Zhu, Zhihao Chen, Tiecheng Cai, Yunbing Wu, Yisong Su, Sibo Ju, Xiangwen Liao

Based on dynamic emotion-semantic vectors and dependency trees, we propose a dynamic correlation graph convolutional network to guide the model in learning context meanings in dialogue and generating empathetic responses.

Dialogue Generation Empathetic Response Generation +1

Large Language Models for Software Engineering: A Systematic Literature Review

1 code implementation21 Aug 2023 Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, Haoyu Wang

Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages.

Systematic Literature Review

BrickPal: Augmented Reality-based Assembly Instructions for Brick Models

no code implementations6 Jul 2023 Yao Shi, Xiaofeng Zhang, Ran Zhang, Zhou Yang, Xiao Tang, Hongni Ye, Yi Wu

The assembly instruction is a mandatory component of Lego-like brick sets. The conventional production of assembly instructions requires a considerable amount of manual fine-tuning, which is intractable for casual users and customized brick sets. Moreover, the traditional paper-based instructions lack expressiveness and interactivity. To tackle the two problems above, we present BrickPal, an augmented reality-based system, which visualizes assembly instructions in an augmented reality head-mounted display.

Source Code Data Augmentation for Deep Learning: A Survey

1 code implementation31 May 2023 Terry Yue Zhuo, Zhou Yang, Zhensu Sun, YuFei Wang, Li Li, Xiaoning Du, Zhenchang Xing, David Lo

This paper fills this gap by conducting a comprehensive and integrative survey of data augmentation for source code, wherein we systematically compile and encapsulate existing literature to provide a comprehensive overview of the field.

Data Augmentation Deep Learning +1

ASDF: A Differential Testing Framework for Automatic Speech Recognition Systems

1 code implementation11 Feb 2023 Daniel Hao Xian Yuen, Andrew Yong Chen Pang, Zhou Yang, Chun Yong Chong, Mei Kuan Lim, David Lo

To address these limitations, our tool incorporates two novel features: (1) a text transformation module to boost the number of generated test cases and uncover more errors in ASR systems and (2) a phonetic analysis module to identify on which phonemes the ASR system tend to produce errors.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Vector Quantization With Self-Attention for Quality-Independent Representation Learning

no code implementations CVPR 2023 Zhou Yang, Weisheng Dong, Xin Li, Mengluan Huang, Yulin Sun, Guangming Shi

During training, we enforce the quantization of features from clean and corrupted images in the same discrete embedding space so that an invariant quality-independent feature representation can be learned to improve the recognition robustness of low-quality images.

Data Augmentation Image Restoration +2

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

1 code implementation7 Oct 2022 Chen Gong, Zhou Yang, Yunpeng Bai, Junda He, Jieke Shi, Kecen Li, Arunesh Sinha, Bowen Xu, Xinwen Hou, David Lo, Tianhao Wang

Our experiments conducted on four tasks and four offline RL algorithms expose a disquieting fact: none of the existing offline RL algorithms is immune to such a backdoor attack.

Autonomous Driving Backdoor Attack +4

Robust control problems of BSDEs coupled with value functions

no code implementations23 Aug 2022 Zhou Yang, Jing Zhang, Chao Zhou

A robust control problem is considered in this paper, where the controlled stochastic differential equations (SDEs) include ambiguity parameters and their coefficients satisfy non-Lipschitz continuous and non-linear growth conditions, the objective function is expressed as a backward stochastic differential equation (BSDE) with the generator depending on the value function.

Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks

no code implementations4 Mar 2022 Zhenxiong Miao, Xingshu Chen, Haizhou Wang, Rui Tang, Zhou Yang, Wenyi Tang

In this paper, we propose an end-to-end method based on community structure and text features for offensive language detection (CT-OLD).

Graph Attention

The $f$-Divergence Reinforcement Learning Framework

no code implementations24 Sep 2021 Chen Gong, Qiang He, Yunpeng Bai, Zhou Yang, Xiaoyu Chen, Xinwen Hou, Xianjie Zhang, Yu Liu, Guoliang Fan

In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards.

Decision Making Deep Reinforcement Learning +4

Fusing Motion Patterns and Key Visual Information for Semantic Event Recognition in Basketball Videos

no code implementations13 Jul 2020 Lifang Wu, Zhou Yang, Qi. Wang, Meng Jian, Boxuan Zhao, Junchi Yan, Chang Wen Chen

Based on the observations, we propose a scheme to fuse global and local motion patterns (MPs) and key visual information (KVI) for semantic event recognition in basketball videos.

Group Activity Recognition Optical Flow Estimation

Discovering Opioid Use Patterns from Social Media for Relapse Prevention

no code implementations2 Dec 2019 Zhou Yang, Spencer Bradshaw, Rattikorn Hewett, Fang Jin

The United States is currently experiencing an unprecedented opioid crisis, and opioid overdose has become a leading cause of injury and death.

Addict Free -- A Smart and Connected Relapse Intervention Mobile App

no code implementations2 Dec 2019 Zhou Yang, Vinay Jayachandra Reddy, Rashmi Kesidi, Fang Jin

It is widely acknowledged that addiction relapse is highly associated with spatial-temporal factors such as some specific places or time periods.

Data Centers Job Scheduling with Deep Reinforcement Learning

no code implementations16 Sep 2019 Sisheng Liang, Zhou Yang, Fang Jin, Yong Chen

Efficient job scheduling on data centers under heterogeneous complexity is crucial but challenging since it involves the allocation of multi-dimensional resources over time and space.

Deep Reinforcement Learning reinforcement-learning +2

Ontology Based Global and Collective Motion Patterns for Event Classification in Basketball Videos

no code implementations16 Mar 2019 Lifang Wu, Zhou Yang, Jiaoyu He, Meng Jian, Yaowen Xu, Dezhong Xu, Chang Wen Chen

Therefore, a semantic event in broadcast basketball videos is closely related to both the global motion (camera motion) and the collective motion.

Classification General Classification +1

Spatial-temporal Multi-Task Learning for Within-field Cotton Yield Prediction

no code implementations16 Nov 2018 Long Nguyen, Jia Zhen, Zhe Lin, Hanxiang Du, Zhou Yang, Wenxuan Guo, Fang Jin

Understanding and accurately predicting within-field spatial variability of crop yield play a key role in site-specific management of crop inputs such as irrigation water and fertilizer for optimized crop production.

Crop Yield Prediction Management +1

Predicting Opioid Relapse Using Social Media Data

no code implementations14 Nov 2018 Zhou Yang, Long Nguyen, Fang Jin

In this paper, we introduce a Generative Adversarial Networks (GAN) model to predict the addiction relapses based on sentiment images and social influences.

Forecasting People's Needs in Hurricane Events from Social Network

no code implementations12 Nov 2018 Long Nguyen, Zhou Yang, Jia Li, Guofeng Cao, Fang Jin

Our proposed sequence to sequence method forecast people's needs more successfully than either of the other models.

Decoder Language Modeling +2

Coordinating Disaster Emergency Response with Heuristic Reinforcement Learning

no code implementations12 Nov 2018 Long Nguyen, Zhou Yang, Jiazhen Zhu, Jia Li, Fang Jin

To improve the efficiency of the emergency response in the immediate aftermath of a disaster, we propose a heuristic multi-agent reinforcement learning scheduling algorithm, named as ResQ, which can effectively schedule the rapid deployment of volunteers to rescue victims in dynamic settings.

Multi-agent Reinforcement Learning reinforcement-learning +3

Analysis of the optimal exercise boundary of American put options with delivery lags

no code implementations8 May 2018 Gechun Liang, Zhou Yang

A make-your-mind-up option is an American derivative with delivery lags.

Map Matching based on Conditional Random Fields and Route Preference Mining for Uncertain Trajectories

no code implementations16 Oct 2014 Xu Ming, Du Yi-man, Wu Jian-ping, Zhou Yang

In order to improve offline map matching accuracy of low-sampling-rate GPS, a map matching algorithm based on conditional random fields (CRF) and route preference mining is proposed.

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