Haodong Zhao

53 papers A* 4A 1B 2Misc 3Journal 34Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
A dual-stream framework to model intra-series and inter-series dynamics for remaining useful life estimation.
J. Supercomput.
Hao Miao, Ni Zhang, Zefei Ning, Haodong Zhao, Jiahui Guo, Li Wang
2026 J jnl
EmbTracker: Traceable Black-box Watermarking for Federated Language Models.
CoRR
Haodong Zhao, Jinming Hu, Yijie Bai, Tian Dong, Wei Du, Zhuosheng Zhang, Yanjiao Chen, Haojin Zhu, Gongshen Liu
2026 J jnl
ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data.
CoRR
Haodong Zhao, Jinming Hu, Zhaomin Wu, Zongru Wu, Wei Du, Junyi Hou, Caibei Zhao, Zhuosheng Zhang, Bingsheng He, Gongshen Liu
2026 J jnl
Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective.
CoRR
Haodong Zhao, Jinming Hu, Gongshen Liu
2026 J jnl
UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities.
CoRR
Qi Jia, Haodong Zhao, Dun Pei, Xiujie Song, Shibo Wang, Zijian Chen, Zicheng Zhang, Xiangyang Zhu, Guangtao Zhai
2025 — conf
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models.
ACL (Findings)
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Guanglu Wan, Xunliang Cai, Zhi Zheng, Tong Xu
2025 J jnl
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models.
CoRR
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Guanglu Wan, Xunliang Cai, Zhi Zheng, Tong Xu
2025 J jnl
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review.
IEEE Trans. Neural Networks Learn. Syst.
Pengzhou Cheng, Zongru Wu, Wei Du, Haodong Zhao, Wei Lu, Gongshen Liu
2025 Misc conf
Conditional-Balanced Adversarial Delta Tuning for Cross-Domain Implicit Discourse Relation Recognition.
ICASSP
Chang Liu, Haowen Sun, Haodong Zhao, Ruifang He, Xu He, Bo Wang
2025 J jnl
Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems.
CoRR
Haodong Zhao, Jidong Li, Zhaomin Wu, Tianjie Ju, Zhuosheng Zhang, Bingsheng He, Gongshen Liu
2025 J jnl
FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing.
CoRR
Haodong Zhao, Peng Peng, Chiyu Chen, Linqing Huang, Gongshen Liu
2025 J jnl
GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?
CoRR
Chiyu Chen, Xinhao Song, Yunkai Chai, Yang Yao, Haodong Zhao, Lijun Li, Jie Li, Yan Teng, Gongshen Liu, Yingchun Wang
2025 J jnl
Judge Before Answer: Can MLLM Discern the False Premise in Question?
CoRR
Jidong Li, Lingyong Fang, Haodong Zhao, Sufeng Duan, Gongshen Liu
2025 J jnl
LLM DNA: Tracing Model Evolution via Functional Representations.
CoRR
Zhaomin Wu, Haodong Zhao, Ziyang Wang, Jizhou Guo, Qian Wang, Bingsheng He
2025 J jnl
Loss-Guided Dynamic Step Adversarial Attack Algorithm for Network Intrusion Detection Systems.
Concurr. Comput. Pract. Exp.
Haodong Zhao, Xiaoyu Du, Ying Du, Roshan Kumar, Jun Jiang
2025 J jnl
Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models.
CoRR
Tianhang Zhao, Wei Du, Haodong Zhao, Sufeng Duan, Gongshen Liu
2025 J jnl
Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning.
CoRR
Haodong Zhao, Chenyan Zhao, Yansi Li, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Vertical Federated Learning in Practice: The Good, the Bad, and the Ugly.
CoRR
Zhaomin Wu, Zhen Qin, Junyi Hou, Haodong Zhao, Qinbin Li, Bingsheng He, Lixin Fan
2025 A* conf
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models.
ICML
Tianjie Ju, Yi Hua, Hao Fei, Zhenyu Shao, Yubin Zheng, Haodong Zhao, Mong-Li Lee, Wynne Hsu, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models.
CoRR
Tianjie Ju, Yi Hua, Hao Fei, Zhenyu Shao, Yubin Zheng, Haodong Zhao, Mong-Li Lee, Wynne Hsu, Zhuosheng Zhang, Gongshen Liu
2025 — conf
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning.
EMNLP (Findings)
Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, Xunliang Cai
2025 J jnl
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning.
CoRR
Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, Xunliang Cai
2024 J jnl
16.2-μW Super Class-AB OTA with current-reuse technique achieving 130.3-μA/μA FoM.
Microelectron. J.
Haodong Zhao, Huizhen Zheng, Shiyue Ma, Keping Wang
2024 J jnl
DynamicAug: Enhancing Transfer Learning Through Dynamic Data Augmentation Strategies Based on Model State.
Neural Process. Lett.
Xinyi Yu, Haodong Zhao, Mingyang Zhang, Yan Wei, Libo Zhou, Linlin Ou
2024 J jnl
Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities.
CoRR
Tianjie Ju, Yiting Wang, Xinbei Ma, Pengzhou Cheng, Haodong Zhao, Yulong Wang, Lifeng Liu, Jian Xie, Zhuosheng Zhang, Gongshen Liu
2024 J jnl
Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition.
CoRR
Haodong Zhao, Ruifang He, Mengnan Xiao, Jing Xu
2024 J jnl
NSmark: Null Space Based Black-box Watermarking Defense Framework for Pre-trained Language Models.
CoRR
Haodong Zhao, Jinming Hu, Peixuan Li, Fangqi Li, Jinrui Sha, Peixuan Chen, Zhuosheng Zhang, Gongshen Liu
2024 Misc conf
NWS: Natural Textual Backdoor Attacks Via Word Substitution.
ICASSP
Wei Du, Tongxin Yuan, Haodong Zhao, Gongshen Liu
2024 A* conf
Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond.
AAAI
Fangqi Li, Haodong Zhao, Wei Du, Shilin Wang
2024 J jnl
Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond.
CoRR
Fangqi Li, Haodong Zhao, Wei Du, Shilin Wang
2024 — conf
UOR: Universal Backdoor Attacks on Pre-trained Language Models.
ACL (Findings)
Wei Du, Peixuan Li, Haodong Zhao, Tianjie Ju, Ge Ren, Gongshen Liu
2023 J jnl
A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network.
CoRR
Haodong Zhao, Wei Du, Junjie Guo, Gongshen Liu
2023 J jnl
A trust-region-like algorithm for expensive multi-objective optimization.
Appl. Soft Comput.
Hongwei Liu, Changcong Zhou, Fuchao Liu, Zunyi Duan, Haodong Zhao
2023 J jnl
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review.
CoRR
Pengzhou Cheng, Zongru Wu, Wei Du, Haodong Zhao, Gongshen Liu
2023 — conf
Dual Hierarchical Contrastive Learning for Multi-level Implicit Discourse Relation Recognition.
NLPCC (2)
Jing Xu, Ruifang He, Haodong Zhao, Huijie Wang, Lei Zeng
2023 — conf
Dual-Prompting Interaction with Entity Representation Enhancement for Event Argument Extraction.
NLPCC (2)
Ruifang He, Mengnan Xiao, Jinsong Ma, Junwei Zhang, Haodong Zhao, Shiqi Zhang, Jie Bai
2023 Misc conf
FedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated Learning.
ICASSP
Haodong Zhao, Wei Du, Fangqi Li, Peixuan Li, Gongshen Liu
2023 J jnl
How dependent basic events with interval-valued probabilities affect fault tree analysis.
Qual. Reliab. Eng. Int.
Qi Chang, Changcong Zhou, Haodong Zhao, Wenxuan Wang, Zhufeng Yue
2023 — conf
Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition.
ACL (1)
Haodong Zhao, Ruifang He, Mengnan Xiao, Jing Xu
2023 B conf
Interactive Capsule Networks with a Novel Dynamic Routing Mechanism for Implicit Discourse Relation Recognition.
IJCNN
Jing Xu, Ruifang He, Haodong Zhao
2023 — conf
Is Continuous Prompt a Combination of Discrete Prompts? Towards a Novel View for Interpreting Continuous Prompts.
ACL (Findings)
Tianjie Ju, Yubin Zheng, Hanyi Wang, Haodong Zhao, Gongshen Liu
2023 A* conf
PLMmark: A Secure and Robust Black-Box Watermarking Framework for Pre-trained Language Models.
AAAI
Peixuan Li, Pengzhou Cheng, Fangqi Li, Wei Du, Haodong Zhao, Gongshen Liu
2023 A* conf
ShiftNAS: Improving One-shot NAS via Probability Shift.
ICCV
Mingyang Zhang, Xinyi Yu, Haodong Zhao, Linlin Ou
2023 J jnl
ShiftNAS: Improving One-shot NAS via Probability Shift.
CoRR
Mingyang Zhang, Xinyi Yu, Haodong Zhao, Linlin Ou
2023 J jnl
UOR: Universal Backdoor Attacks on Pre-trained Language Models.
CoRR
Wei Du, Peixuan Li, Boqun Li, Haodong Zhao, Gongshen Liu
2023 — conf
Unleashing Pre-trained Masked Language Model Knowledge for Label Signal Guided Event Detection.
DASFAA (3)
Mengnan Xiao, Ruifang He, Junwei Zhang, Jinsong Ma, Haodong Zhao
2022 A conf
A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network.
INTERSPEECH
Haodong Zhao, Wei Du, Junjie Guo, Gongshen Liu
2022 J jnl
A general hierarchical ensemble-learning framework for structural reliability analysis.
Reliab. Eng. Syst. Saf.
Changcong Zhou, Hanlin Zhang, Marcos A. Valdebenito, Haodong Zhao
2022 J jnl
A unified approach for global sensitivity analysis based on active subspace and Kriging.
Reliab. Eng. Syst. Saf.
Changcong Zhou, Zhuangke Shi, Sergei S. Kucherenko, Haodong Zhao
2022 J jnl
Reduce Communication Costs and Preserve Privacy: Prompt Tuning Method in Federated Learning.
CoRR
Haodong Zhao, Wei Du, Fangqi Li, Peixuan Li, Gongshen Liu
2021 B conf
Bridging the Gap of Dimensions in Distillation: Understanding the knowledge transfer between different-dimensional semantic spaces.
IJCNN
Zhiyuan Ma, Ziyue Song, Haodong Zhao, Kui Meng, Gongshen Liu
2021 J jnl
Fault Tree Analysis With Interval Uncertainty: A Case Study of the Aircraft Flap Mechanism.
IEEE Trans. Reliab.
Changcong Zhou, Qi Chang, Haodong Zhao, Mengyao Ji, Zhuangke Shi
2021 — conf
Speaker Verification with Disentangled Self-attention.
ICONIP (1)
Junjie Guo, Zhiyuan Ma, Haodong Zhao, Gongshen Liu, Xiaoyong Li