Cheng Yang

Cheng Yang

Auto-generated profile, based on publicly available information

Cheng Yang

College of Computer, National University of Defense Technology, Changsha, Hunan, China and State Key Laboratory of Complex & Critical Software Environment, Changsha, Hunan, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2019 in Frontiers of Information Technology & Electronic Engineering
Verified
Journal Article
Closed access
PDF file
CYCheng Yang
Cheng Yang
QFQiang Fan
Qiang Fan
TWTao Wang
Tao Wang
GYGang Yin
Gang Yin
XZXun-Hui Zhang
Xun-Hui Zhang
HWHua-Min Wang
Hua-Min Wang
With the deep integration of software collaborative development and social networking, social coding represents a new style of software production and creation paradigm. Because of their good...

18 May 2018 in Journal of Central South University
Verified
Journal Article
Closed access
PDF file
CYCheng Yang
Cheng Yang
XZXun-Hui Zhang
Xun-Hui Zhang
LZLing-Bin Zeng
Ling-Bin Zeng
QFQiang Fan
Qiang Fan
TWTao Wang
Tao Wang
HWHuai-Min Wang
Huai-Min Wang

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YZYuanzhao Zhai
Yuanzhao Zhai
TYTingkai Yang
Tingkai Yang
KXKele Xu
Kele Xu
Dawei FengDawei Feng
Dawei Feng
CYCheng Yang
Cheng Yang
HWHuaimin Wang
Huaimin Wang
Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents still face challenges in tasks that require multiple decision-making steps. Estimating the value of actions in specific tasks is difficult when intermediate actions are neither appropriately rewarded nor penalized. In this paper, we propose leveraging a task-relevant Q-value model to guide action selection. Specifically, we first collect decision-making trajectories annotated with step-level Q values via Monte Carlo Tree Search (MCTS) and construct preference data. We then use another LLM to fit these preferences through step-level Direct Policy Optimization (DPO), which serves as the Q-value model. During inference, at each decision-making step, LLM agents select the action with the highest Q value before interacting with the environment. We apply our method to various open-source and API-based LLM agents, demonstrating that Q-value models significantly improve their performance. Notably, the performance of the agent built with Phi-3-mini-4k-instruct improved by 103% on WebShop and 75% on HotPotQA when enhanced with Q-value models, even surpassing GPT-4o-mini. Additionally, Q-value models offer several advantages, such as generalization to different LLM agents and seamless integration with existing prompting strategies.

28 October 2024
Verified
Conference Paper
Open access
MTMingsheng Tu
Mingsheng Tu
TWTianjiao Wan
Tianjiao Wan
QXQisheng Xu
Qisheng Xu
XJXinhao Jiang
Xinhao Jiang
KXKele Xu
Kele Xu
CYCheng Yang
Cheng Yang
The prediction task of social media popularity aims to automatically forecast the future popularity of the posts by leveraging vast amounts of social media data. This data encompasses diverse visual and textual content, including photos, categories, custom tags, temporal information, and geographical data. Existing methods have explored multiple feature types to enhance popularity prediction. Despite their success, visual and textual features-both crucial pieces of information-are often simply concatenated after extraction, ignoring the divergence between these two feature spaces. In this paper, we propose a method to project visual and language information into an aligned semantic representation, thereby uncovering intricate associations between these two modalities. Specifically, we leverage the BLIP-2 model to understand and generate visual description text that encapsulates the content of photos. Semantic embeddings are then extracted from all available visual and textual information. Additionally, we deeply exploit user-related behavior and characteristic information to extract features, uncovering hidden clues for post popularity prediction. Leveraging these improvements, we conduct extensive experiments to demonstrate the effectiveness of our proposed method.

12 March 2024 in IEEE Open Journal of Engineering in Medicine and Biology
Verified
Journal Article
Open access
KXKele Xu
Kele Xu
KYKang You
Kang You
BZBoqing Zhu
Boqing Zhu
MFMing Feng
Ming Feng
Dawei FengDawei Feng
Dawei Feng
CYCheng Yang
Cheng Yang
Recently, deep learning-based methods have emerged as the preferred approach for ultrasound data analysis. However, these methods often require large-scale annotated datasets for training deep models, which are not readily available in practical scenarios. Additionally, the presence of speckle noise and other imaging artifacts can introduce numerous hard examples for ultrasound data classification. In this paper, drawing inspiration from self-supervised learning techniques, we present a pre-training method based on mask modeling specifically designed for ultrasound data. Our study investigates three different mask modeling strategies: random masking, vertical masking, and horizontal masking. By employing these strategies, our pre-training approach aims to predict the masked portion of the ultrasound images. Notably, our method does not rely on externally labeled data, allowing us to extract representative features without the need for human annotation. Consequently, we can leverage unlabeled datasets for pre-training. Furthermore, to address the challenges posed by hard samples in ultrasound data, we propose a novel hard sample mining strategy. To evaluate the effectiveness of our proposed method, we conduct experiments on two datasets. The experimental results demonstrate that our approach outperforms other state-of-the-art methods in ultrasound image classification. This indicates the superiority of our pre-training method and its ability to extract discriminative features from ultrasound data, even in the presence of hard examples.

13 July 2025
Verified
Conference Paper
Open access
YZYuanzhao Zhai
Yuanzhao Zhai
HLHuanxi Liu
Huanxi Liu
ZZZhuo Zhang
Zhuo Zhang
TLTong Lin
Tong Lin
KXKele Xu
Kele Xu
HWHuaimin Wang
Huaimin Wang