Hongyang Zhang

96 papers A* 27A 5Journal 55Unranked 8

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training. IEEE Trans. Inf. Forensics Secur. Haochen Sun, Tonghe Bai, Jason Li, Hongyang Zhang
2024	A*	`conf`	A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models. ICML Yihan Wu, Zhengmian Hu, Junfeng Guo, Hongyang Zhang, Heng Huang
2024	A*	`conf`	AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls. ICML Yu Du, Fangyun Wei, Hongyang Zhang
2024	J	`jnl`	AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls. CoRR Yu Du, Fangyun Wei, Hongyang Zhang
2024	—	`conf`	Direct-Effect Risk Minimization for Domain Generalization. ECML/PKDD (3) Yuhui Li, Zejia Wu, Chao Zhang, Hongyang Zhang
2024	J	`jnl`	Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions. CoRR Yihan Wu, Ruibo Chen, Zhengmian Hu, Yanshuo Chen, Junfeng Guo, Hongyang Zhang, Heng Huang
2024	A*	`conf`	EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees. EMNLP Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
2024	J	`jnl`	EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees. CoRR Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
2024	A*	`conf`	EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty. ICML Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
2024	J	`jnl`	EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty. CoRR Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
2024	A*	`conf`	Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains. AAAI Yimu Wang, Yihan Wu, Hongyang Zhang
2024	A*	`conf`	RAIN: Your Language Models Can Align Themselves without Finetuning. ICLR Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang
2024	J	`jnl`	Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning. IEEE Trans. Pattern Anal. Mach. Intell. Lang Huang, Chao Zhang, Hongyang Zhang
2024	A*	`conf`	Unbiased Watermark for Large Language Models. ICLR Zhengmian Hu, Lichang Chen, Xidong Wu, Yihan Wu, Hongyang Zhang, Heng Huang
2024	A*	`conf`	zkLLM: Zero Knowledge Proofs for Large Language Models. CCS Haochen Sun, Jason Li, Hongyang Zhang
2024	J	`jnl`	zkLLM: Zero Knowledge Proofs for Large Language Models. CoRR Haochen Sun, Jason Li, Hongyang Zhang
2023	A*	`conf`	A Law of Robustness beyond Isoperimetry. ICML Yihan Wu, Heng Huang, Hongyang Zhang
2023	J	`jnl`	An Analysis of Robustness of Non-Lipschitz Networks. J. Mach. Learn. Res. Maria-Florina Balcan, Avrim Blum, Dravyansh Sharma, Hongyang Zhang
2023	A*	`conf`	Causal Balancing for Domain Generalization. ICLR Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang
2023	A*	`conf`	Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets. CVPR Yimu Wang, Dinghuai Zhang, Yihan Wu, Heng Huang, Hongyang Zhang
2023	J	`jnl`	Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets. CoRR Yimu Wang, Dinghuai Zhang, Yihan Wu, Heng Huang, Hongyang Zhang
2023	J	`jnl`	DiPmark: A Stealthy, Efficient and Resilient Watermark for Large Language Models. CoRR Yihan Wu, Zhengmian Hu, Hongyang Zhang, Heng Huang
2023	J	`jnl`	Investigating the Existence of "Secret Language" in Language Models. CoRR Yimu Wang, Peng Shi, Hongyang Zhang
2023	A	`conf`	Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games. AISTATS Maria-Florina Balcan, Rattana Pukdee, Pradeep Ravikumar, Hongyang Zhang
2023	J	`jnl`	RAIN: Your Language Models Can Align Themselves without Finetuning. CoRR Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang
2023	J	`jnl`	Recovery From Non-Decomposable Distance Oracles. IEEE Trans. Inf. Theory Zhuangfei Hu, Xinda Li, David P. Woodruff, Hongyang Zhang, Shufan Zhang
2023	A	`conf`	Recovery from Non-Decomposable Distance Oracles. ITCS Zhuangfei Hu, Xinda Li, David P. Woodruff, Hongyang Zhang, Shufan Zhang
2023	—	`conf`	Towards Transferable Unrestricted Adversarial Examples with Minimum Changes. SaTML Fangcheng Liu, Chao Zhang, Hongyang Zhang
2023	J	`jnl`	Unbiased Watermark for Large Language Models. CoRR Zhengmian Hu, Lichang Chen, Xidong Wu, Yihan Wu, Hongyang Zhang, Heng Huang
2023	A*	`conf`	Understanding the Impact of Adversarial Robustness on Accuracy Disparity. ICML Yuzheng Hu, Fan Wu, Hongyang Zhang, Han Zhao
2023	J	`jnl`	zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training. CoRR Haochen Sun, Hongyang Zhang
2023	J	`jnl`	zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training. IACR Cryptol. ePrint Arch. Haochen Sun, Hongyang Zhang
2022	J	`jnl`	A Closer Look at Robustness to L-infinity and Spatial Perturbations and their Composition. CoRR Luke Rowe, Benjamin Thérien, Krzysztof Czarnecki, Hongyang Zhang
2022	A*	`conf`	Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness. NeurIPS Avrim Blum, Omar Montasser, Greg Shakhnarovich, Hongyang Zhang
2022	J	`jnl`	Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness. CoRR Avrim Blum, Omar Montasser, Greg Shakhnarovich, Hongyang Zhang
2022	A*	`conf`	Building Robust Ensembles via Margin Boosting. ICML Dinghuai Zhang, Hongyang Zhang, Aaron C. Courville, Yoshua Bengio, Pradeep Ravikumar, Arun Sai Suggala
2022	J	`jnl`	Building Robust Ensembles via Margin Boosting. CoRR Dinghuai Zhang, Hongyang Zhang, Aaron C. Courville, Yoshua Bengio, Pradeep Ravikumar, Arun Sai Suggala
2022	J	`jnl`	Causal Balancing for Domain Generalization. CoRR Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang
2022	A*	`conf`	Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking. EMNLP Minghan Li, Xinyu Zhang, Ji Xin, Hongyang Zhang, Jimmy Lin
2022	J	`jnl`	Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking. CoRR Minghan Li, Xinyu Zhang, Ji Xin, Hongyang Zhang, Jimmy Lin
2022	J	`jnl`	Direct-Effect Risk Minimization for Domain Generalization. CoRR Yuhui Li, Zejia Wu, Chao Zhang, Hongyang Zhang
2022	J	`jnl`	How Many Data Are Needed for Robust Learning? CoRR Hongyang Zhang, Yihan Wu, Heng Huang
2022	J	`jnl`	Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games. CoRR Maria-Florina Balcan, Rattana Pukdee, Pradeep Ravikumar, Hongyang Zhang
2022	J	`jnl`	Recovery from Non-Decomposable Distance Oracles. CoRR Zhuangfei Hu, Xinda Li, David P. Woodruff, Hongyang Zhang, Shufan Zhang
2022	A*	`conf`	RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval. ICML Yihan Wu, Hongyang Zhang, Heng Huang
2022	J	`jnl`	RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval. CoRR Yihan Wu, Hongyang Zhang, Heng Huang
2022	J	`jnl`	Towards Robust Dataset Learning. CoRR Yihan Wu, Xinda Li, Florian Kerschbaum, Heng Huang, Hongyang Zhang
2022	J	`jnl`	Towards Transferable Unrestricted Adversarial Examples with Minimum Changes. CoRR Fangcheng Liu, Chao Zhang, Hongyang Zhang
2022	J	`jnl`	Understanding the Impact of Adversarial Robustness on Accuracy Disparity. CoRR Yuzheng Hu, Fan Wu, Hongyang Zhang, Han Zhao
2021	—	`conf`	Adversarial Robustness of Stabilized Neural ODE Might be from Obfuscated Gradients. MSML Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao
2021	J	`jnl`	Self-Adaptive Training: Bridging the Supervised and Self-Supervised Learning. CoRR Lang Huang, Chao Zhang, Hongyang Zhang
2021	J	`jnl`	Unrestricted Adversarial Attacks on ImageNet Competition. CoRR Yuefeng Chen, Xiaofeng Mao, Yuan He, Hui Xue, Chao Li, Yinpeng Dong, Qi-An Fu, Xiao Yang, Wenzhao Xiang, Tianyu Pang, Hang Su, Jun Zhu, Fangcheng Liu, Chao Zhang, Hongyang Zhang, Yichi Zhang, Shilong Liu, Chang Liu, Wenzhao Xiang, Yajie Wang, Huipeng Zhou, Haoran Lyu, Yidan Xu, Zixuan Xu, Taoyu Zhu, Wenjun Li, Xianfeng Gao, Guoqiu Wang, Huanqian Yan, Ying Guo, Chaoning Zhang, Zheng Fang, Yang Wang, Bingyang Fu, Yunfei Zheng, Yekui Wang, Haorong Luo, Zhen Yang
2020	A*	`conf`	A Closer Look at Accuracy vs. Robustness. NeurIPS Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Ruslan Salakhutdinov, Kamalika Chaudhuri
2020	J	`jnl`	Adversarial Robustness Through Local Lipschitzness. CoRR Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Ruslan Salakhutdinov, Kamalika Chaudhuri
2020	J	`jnl`	Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients. CoRR Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao
2020	—	`conf`	Design and Interpretation of Universal Adversarial Patches in Face Detection. ECCV (17) Xiao Yang, Fangyun Wei, Hongyang Zhang, Jun Zhu
2020	J	`jnl`	On the Power of Abstention and Data-Driven Decision Making for Adversarial Robustness. CoRR Maria-Florina Balcan, Avrim Blum, Dravyansh Sharma, Hongyang Zhang
2020	J	`jnl`	Random Smoothing Might be Unable to Certify L∞ Robustness for High-Dimensional Images. J. Mach. Learn. Res. Avrim Blum, Travis Dick, Naren Manoj, Hongyang Zhang
2020	J	`jnl`	Random Smoothing Might be Unable to Certify 𝓁 CoRR Avrim Blum, Travis Dick, Naren Manoj, Hongyang Zhang
2020	A*	`conf`	Self-Adaptive Training: beyond Empirical Risk Minimization. NeurIPS Lang Huang, Chao Zhang, Hongyang Zhang
2020	J	`jnl`	Self-Adaptive Training: beyond Empirical Risk Minimization. CoRR Lang Huang, Chao Zhang, Hongyang Zhang
2019	A	`conf`	Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-Convex. AISTATS Hongyang Zhang, Junru Shao, Ruslan Salakhutdinov
2019	J	`jnl`	Design and Interpretation of Universal Adversarial Patches in Face Detection. CoRR Xiao Yang, Fangyun Wei, Hongyang Zhang, Xiang Ming, Jun Zhu
2019	A*	`conf`	Efficient Symmetric Norm Regression via Linear Sketching. NeurIPS Zhao Song, Ruosong Wang, Lin F. Yang, Hongyang Zhang, Peilin Zhong
2019	J	`jnl`	Efficient Symmetric Norm Regression via Linear Sketching. CoRR Zhao Song, Ruosong Wang, Lin F. Yang, Hongyang Zhang, Peilin Zhong
2019	—	`—`	New Advances in Sparse Learning, Deep Networks, and Adversarial Learning: Theory and Applications. Hongyang Zhang
2019	J	`jnl`	Non-Convex Matrix Completion and Related Problems via Strong Duality. J. Mach. Learn. Res. Maria-Florina Balcan, Yingyu Liang, Zhao Song, David P. Woodruff, Hongyang Zhang
2019	J	`jnl`	Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation. CoRR Chen Dan, Hong Wang, Hongyang Zhang, Yuchen Zhou, Pradeep Ravikumar
2019	A*	`conf`	Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation. NeurIPS Chen Dan, Hong Wang, Hongyang Zhang, Yuchen Zhou, Pradeep Ravikumar
2019	A*	`conf`	Testing Matrix Rank, Optimally. SODA Maria-Florina Balcan, Yi Li, David P. Woodruff, Hongyang Zhang
2019	A*	`conf`	Theoretically Principled Trade-off between Robustness and Accuracy. ICML Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael I. Jordan
2019	J	`jnl`	Theoretically Principled Trade-off between Robustness and Accuracy. CoRR Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael I. Jordan
2018	J	`jnl`	Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex. CoRR Hongyang Zhang, Junru Shao, Ruslan Salakhutdinov
2018	A*	`conf`	Improved Algorithms for Adaptive Compressed Sensing. ICALP Vasileios Nakos, Xiaofei Shi, David P. Woodruff, Hongyang Zhang
2018	J	`jnl`	Improved Algorithms for Adaptive Compressed Sensing. CoRR Vasileios Nakos, Xiaofei Shi, David P. Woodruff, Hongyang Zhang
2018	A	`conf`	Matrix Completion and Related Problems via Strong Duality. ITCS Maria-Florina Balcan, Yingyu Liang, David P. Woodruff, Hongyang Zhang
2018	J	`jnl`	On the Applications of Robust PCA in Image and Video Processing. Proc. IEEE Thierry Bouwmans, Sajid Javed, Hongyang Zhang, Zhouchen Lin, Ricardo Otazo
2018	J	`jnl`	Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures. CoRR Hongyang Zhang, Susu Xu, Jiantao Jiao, Pengtao Xie, Ruslan Salakhutdinov, Eric P. Xing
2018	J	`jnl`	Testing Matrix Rank, Optimally. CoRR Maria-Florina Balcan, Yi Li, David P. Woodruff, Hongyang Zhang
2017	A*	`conf`	Differentially Private Clustering in High-Dimensional Euclidean Spaces. ICML Maria-Florina Balcan, Travis Dick, Yingyu Liang, Wenlong Mou, Hongyang Zhang
2017	A*	`conf`	Fast Compressive Phase Retrieval under Bounded Noise. AAAI Hongyang Zhang, Shan You, Zhouchen Lin, Chao Xu
2017	—	`conf`	Noise-Tolerant Interactive Learning Using Pairwise Comparisons. NIPS Yichong Xu, Hongyang Zhang, Aarti Singh, Artur Dubrawski, Kyle Miller
2017	J	`jnl`	Optimal Sample Complexity for Matrix Completion and Related Problems via 𝓁s CoRR Maria-Florina Balcan, Yingyu Liang, David P. Woodruff, Hongyang Zhang
2017	J	`jnl`	S-Concave Distributions: Towards Broader Distributions for Noise-Tolerant and Sample-Efficient Learning Algorithms. CoRR Maria-Florina Balcan, Hongyang Zhang
2017	—	`conf`	Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions. NIPS Maria-Florina Balcan, Hongyang Zhang
2016	J	`jnl`	Completing Low-Rank Matrices With Corrupted Samples From Few Coefficients in General Basis. IEEE Trans. Inf. Theory Hongyang Zhang, Zhouchen Lin, Chao Zhang
2016	A*	`conf`	Learning and 1-bit Compressed Sensing under Asymmetric Noise. COLT Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Hongyang Zhang
2016	—	`conf`	Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling. NIPS Maria-Florina Balcan, Hongyang Zhang
2016	J	`jnl`	Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling. CoRR Maria-Florina Balcan, Hongyang Zhang
2015	J	`jnl`	Completing Low-Rank Matrices with Corrupted Samples from Few Coefficients in General Basis. CoRR Hongyang Zhang, Zhouchen Lin, Chao Zhang
2015	A*	`conf`	Exact Recoverability of Robust PCA via Outlier Pursuit with Tight Recovery Bounds. AAAI Hongyang Zhang, Zhouchen Lin, Chao Zhang, Edward Y. Chang
2015	A	`conf`	Manifold-Regularized Selectable Factor Extraction for Semi-supervised Image Classification. BMVC Xin Shi, Chao Zhang, Fangyun Wei, Hongyang Zhang, Yiyuan She
2015	J	`jnl`	Relations Among Some Low-Rank Subspace Recovery Models. Neural Comput. Hongyang Zhang, Zhouchen Lin, Chao Zhang, Junbin Gao
2014	J	`jnl`	Relations among Some Low Rank Subspace Recovery Models. CoRR Hongyang Zhang, Zhouchen Lin, Chao Zhang, Junbin Gao
2014	J	`jnl`	Robust latent low rank representation for subspace clustering. Neurocomputing Hongyang Zhang, Zhouchen Lin, Chao Zhang, Junbin Gao
2013	—	`conf`	A Counterexample for the Validity of Using Nuclear Norm as a Convex Surrogate of Rank. ECML/PKDD (2) Hongyang Zhang, Zhouchen Lin, Chao Zhang