no code implementations • 27 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%.
no code implementations • 2 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.
no code implementations • 16 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.
no code implementations • 15 Nov 2024 • Xiaofei Zhu, Jiawei Cheng, Zhou Yang, Zhuo Chen, Qingyang Wang, Jianfeng Yao
Then, it introduces a hierarchical distillation framework to maintain the consistency between modality representations with different granularities.
Emotion Recognition in Conversation
Multimodal Emotion Recognition
+1
1 code implementation • 14 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.
no code implementations • 4 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.
1 code implementation • 25 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.
1 code implementation • 28 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.
1 code implementation • 27 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.
no code implementations • 8 Jan 2024 • Wei Hung Pan, Ming Jie Chok, Jonathan Leong Shan Wong, Yung Xin Shin, Yeong Shian Poon, Zhou Yang, Chun Yong Chong, David Lo, Mei Kuan Lim
This is achieved by generating code in response to a given question using different variants.
1 code implementation • 21 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.
no code implementations • 6 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.
1 code implementation • 31 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.
1 code implementation • 11 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
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.
1 code implementation • 7 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.
no code implementations • 23 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.
no code implementations • 4 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).
no code implementations • 24 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.
no code implementations • 13 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.
no code implementations • 2 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.
no code implementations • 2 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.
no code implementations • 16 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.
no code implementations • 16 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.
no code implementations • 16 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.
no code implementations • 14 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.
no code implementations • 12 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.
no code implementations • 12 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
no code implementations • 8 May 2018 • Gechun Liang, Zhou Yang
A make-your-mind-up option is an American derivative with delivery lags.
no code implementations • 16 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.