Changsheng Wang

According to our database, Changsheng Wang authored at least 26 papers between 2010 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered.

Sijia Liu, Yicheng Lang, Soumyadeep Pal, Changsheng Wang, Yancheng Huang, Chongyu Fan, James Diffenderfer, Bhavya Kailkhura, Yihua Zhang

CoRR, May, 2026

Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization.

Yancheng Huang, Changsheng Wang, Chongyu Fan, Yicheng Lang, Bingqi Shang, Yang Zhang, Mingyi Hong, Qing Qu, Alvaro Velasquez, Sijia Liu

CoRR, April, 2026

Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization.

Yicheng Lang, Changsheng Wang, Yihua Zhang, Mingyi Hong, Zheng Zhang, Wotao Yin, Sijia Liu

CoRR, February, 2026

Classified-RRT*: Node classification RRT*-based algorithm with improved solution performance and convergence rate.

Zhihua Xiong, Wenbin Hou, Changsheng Wang, Hao Chen

Expert Syst. Appl., 2026

2025

Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization.

Changsheng Wang, Xin Chen, Siqi Liu, Ke Ding

CoRR, October, 2025

LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics.

Chongyu Fan, Changsheng Wang, Yancheng Huang, Soumyadeep Pal, Sijia Liu

CoRR, October, 2025

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning.

Yicheng Lang, Yihua Zhang, Chongyu Fan, Changsheng Wang, Jinghan Jia, Sijia Liu

CoRR, October, 2025

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks.

Soumyadeep Pal, Changsheng Wang, James Diffenderfer, Bhavya Kailkhura, Sijia Liu

CoRR, April, 2025

The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization.

Yihua Zhang, Changsheng Wang, Yiwei Chen, Chongyu Fan, Jinghan Jia, Sijia Liu

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning.

Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills.

Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data.

Changsheng Wang, Yihua Zhang, Dennis Wei, Jinghan Jia, Pin-Yu Chen, Sijia Liu

Proceedings of the 18th ACM Workshop on Artificial Intelligence and Security, 2025

2024

How generous interface affect user experience and behavior: Evaluating the information display interface for museum cultural heritage.

Qiang Li, Peng Wang, Zexue Liu, Changsheng Wang

Comput. Animat. Virtual Worlds, 2024

Human or Algorithm? The Visual Turing Test of AI-Generated Images.

Changsheng Wang

J. Multim. Inf. Syst., 2024

Deep Transfer Learning Based on LSTM Model for Reservoir Flood Forecasting.

Qiliang Zhu, Changsheng Wang, Wenchao Jin, Jianxun Ren, Xueting Yu

Int. J. Data Warehous. Min., 2024

Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors.

Jiachen Sun, Changsheng Wang, Jiongxiao Wang, Yiwei Zhang, Chaowei Xiao

CoRR, 2024

Art Innovation or Plagiarism? Chinese Students' Attitudes Toward AI Painting Technology and Influencing Factors.

Changsheng Wang

IEEE Access, 2024

Uplift Modeling for Target User Attacks on Recommender Systems.

Wenjie Wang, Changsheng Wang, Fuli Feng, Wentao Shi, Daizong Ding, Tat-Seng Chua

Proceedings of the ACM on Web Conference 2024, 2024

2023

The vibration control of magnetorheological elastomer damper for eccentric workshop.

Changsheng Wang

Int. J. Crit. Infrastructures, 2023

RecAD: Towards A Unified Library for Recommender Attack and Defense.

Changsheng Wang, Jianbai Ye, Wenjie Wang, Chongming Gao, Fuli Feng, Xiangnan He

Proceedings of the 17th ACM Conference on Recommender Systems, 2023

Research on smart classroom learning paths and effect testing and evaluation technology based on machine learning algorithm.

Yingchuan He, Changsheng Wang, Xinyuan Cao

Proceedings of the 6th International Conference on E-Business, 2023

2022

Enhanced ant colony algorithm with communication mechanism for mobile robot path planning.

Wenbin Hou, Zhihua Xiong, Changsheng Wang, Howard Chen

Robotics Auton. Syst., 2022

2018

Robust Widely Widely Beamforming via the Technique of Shrinkage for Steering Vector Estimation.

Jiangbo Liu, Wei Xie, Changsheng Wang, Qun Wan

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2012

Filling Holes in Triangular Meshes in Engineering.

Ping Hu, Changsheng Wang, Baojun Li, Mingzeng Liu

J. Softw., 2012

2010

Image-Driven Panel Design via Feature-Preserving Mesh Deformation.

Baojun Li, Xiuping Liu, Yanqi Liu, Ping Hu, Mingzeng Liu, Changsheng Wang

Proceedings of the Computer and Computing Technologies in Agriculture IV, 2010

Research on GPS attitude determination based on DPSO.

Na Xia, Changsheng Wang, Xingqi Shang, Chunhua Yu

Proceedings of the Sixth International Conference on Natural Computation, 2010