Junyuan Hong - RankMe

65 papers A* 21A 1Journal 37Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment. CoRR Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu
2025	J	`jnl`	AD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback. CoRR Yunhao Yang, Junyuan Hong, Gabriel Jacob Perin, Zhiwen Fan, Li Yin, Zhangyang Wang, Ufuk Topcu
2025	J	`jnl`	CARE-RAG - Clinical Assessment and Reasoning in RAG. CoRR Deepthi Potluri, Aby M. Mathew, Jeffrey B. DeWitt, Alexander L. Rasgon, Yide Hao, Junyuan Hong, Ying Ding
2025	—	`conf`	Extracting and Understanding the Superficial Knowledge in Alignment. NAACL (Long Papers) Runjin Chen, Gabriel J. Perin, Xuxi Chen, Xilun Chen, Yan Han, Nina S. T. Hirata, Junyuan Hong, Bhavya Kailkhura
2025	J	`jnl`	Extracting and Understanding the Superficial Knowledge in Alignment. CoRR Runjin Chen, Gabriel J. Perin, Xuxi Chen, Xilun Chen, Yan Han, Nina S. T. Hirata, Junyuan Hong, Bhavya Kailkhura
2025	—	`conf`	FedKDD 2025: The 2025 International Joint Workshop on Federated Learning for Data Mining and Graph Analytics. KDD (2) Carl Yang, Guancheng Wan, Zhuangdi Zhu, Zheng Xu, Junyuan Hong, Nathalie Baracaldo, Neil Shah, Salman Avestimehr, Jiayu Zhou
2025	A*	`conf`	GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning. ICML Zhen Xiang, Linzhi Zheng, YanJie Li, Junyuan Hong, Qinbin Li, Han Xie, Jiawei Zhang, Zidi Xiong, Chulin Xie, Carl Yang, Dawn Song, Bo Li
2025	—	`conf`	GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing. NAACL (Long Papers) Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang, Eunhye Grace Ko, Lily Boddy, Chenan Wang, Tianhao Li, Alexander Rasgon, Junyuan Hong, Min Kyung Lee, Chenxi Yuan, Qi Long, Ying Ding, Tianlong Chen, Kaidi Xu
2025	J	`jnl`	GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing. CoRR Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang, Eunhye Grace Ko, Lily Boddy, Chenan Wang, Tianhao Li, Alexander Rasgon, Junyuan Hong, Min Kyung Lee, Chenxi Yuan, Qi Long, Ying Ding, Tianlong Chen, Kaidi Xu
2025	J	`jnl`	LLMs Can Get "Brain Rot"! CoRR Shuo Xing, Junyuan Hong, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, Zhangyang Wang
2025	J	`jnl`	LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning. CoRR Gabriel J. Perin, Runjin Chen, Xuxi Chen, Nina S. T. Hirata, Zhangyang Wang, Junyuan Hong
2025	A*	`conf`	MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models. EMNLP Shrey Pandit, Jiawei Xu, Junyuan Hong, Zhangyang Wang, Tianlong Chen, Kaidi Xu, Ying Ding
2025	J	`jnl`	MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models. CoRR Shrey Pandit, Jiawei Xu, Junyuan Hong, Zhangyang Wang, Tianlong Chen, Kaidi Xu, Ying Ding
2025	J	`jnl`	More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment. CoRR Yifan Wang, Runjin Chen, Bolian Li, David Cho, Yihe Deng, Ruqi Zhang, Tianlong Chen, Zhangyang Wang, Ananth Grama, Junyuan Hong
2025	J	`jnl`	SEAL: Steerable Reasoning Calibration of Large Language Models for Free. CoRR Runjin Chen, Zhenyu Zhang, Junyuan Hong, Souvik Kundu, Zhangyang Wang
2025	J	`jnl`	Scaling Textual Gradients via Sampling-Based Momentum. CoRR Zixin Ding, Junyuan Hong, Jiachen T. Wang, Zinan Lin, Zhangyang Wang, Yuxin Chen
2024	A*	`conf`	DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer. ICLR Junyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang
2024	A*	`conf`	Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression. ICML Junyuan Hong, Jinhao Duan, Chenhui Zhang, Zhangheng Li, Chulin Xie, Kelsey Lieberman, James Diffenderfer, Brian R. Bartoldson, Ajay Kumar Jaiswal, Kaidi Xu, Bhavya Kailkhura, Dan Hendrycks, Dawn Song, Zhangyang Wang, Bo Li
2024	J	`jnl`	Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression. CoRR Junyuan Hong, Jinhao Duan, Chenhui Zhang, Zhangheng Li, Chulin Xie, Kelsey Lieberman, James Diffenderfer, Brian R. Bartoldson, Ajay Jaiswal, Kaidi Xu, Bhavya Kailkhura, Dan Hendrycks, Dawn Song, Zhangyang Wang, Bo Li
2024	J	`jnl`	DeepOSets: Non-Autoregressive In-Context Learning of Supervised Learning Operators. CoRR Shao-Ting Chiu, Junyuan Hong, Ulisses Braga-Neto
2024	A*	`conf`	FedKDD: International Joint Workshop on Federated Learning for Data Mining and Graph Analytics. KDD Junyuan Hong, Carl Yang, Zhuangdi Zhu, Zheng Xu, Nathalie Baracaldo, Neil Shah, Salman Avestimehr, Jiayu Zhou
2024	J	`jnl`	GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning. CoRR Zhen Xiang, Linzhi Zheng, YanJie Li, Junyuan Hong, Qinbin Li, Han Xie, Jiawei Zhang, Zidi Xiong, Chulin Xie, Carl Yang, Dawn Song, Bo Li
2024	J	`jnl`	LLM-PBE: Assessing Data Privacy in Large Language Models. CoRR Qinbin Li, Junyuan Hong, Chulin Xie, Jeffrey Tan, Rachel Xin, Junyi Hou, Xavier Yin, Zhun Wang, Dan Hendrycks, Zhangyang Wang, Bo Li, Bingsheng He, Dawn Song
2024	J	`jnl`	LLM-PBE: Assessing Data Privacy in Large Language Models. Proc. VLDB Endow. Qinbin Li, Junyuan Hong, Chulin Xie, Jeffrey Tan, Rachel Xin, Junyi Hou, Xavier Yin, Zhun Wang, Dan Hendrycks, Zhangyang Wang, Bo Li, Bingsheng He, Dawn Song
2024	A	`conf`	On the Generalization Ability of Unsupervised Pretraining. AISTATS Yuyang Deng, Junyuan Hong, Jiayu Zhou, Mehrdad Mahdavi
2024	J	`jnl`	On the Generalization Ability of Unsupervised Pretraining. CoRR Yuyang Deng, Junyuan Hong, Jiayu Zhou, Mehrdad Mahdavi
2024	A*	`conf`	Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark. ICML Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, Tianlong Chen
2024	J	`jnl`	Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark. CoRR Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, Tianlong Chen
2024	A*	`conf`	Safe and Robust Watermark Injection with a Single OoD Image. ICLR Shuyang Yu, Junyuan Hong, Haobo Zhang, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2024	—	`conf`	Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk. SaTML Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang
2024	J	`jnl`	Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk. CoRR Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang
2023	J	`jnl`	DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer. CoRR Junyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang
2023	J	`jnl`	FedNoisy: Federated Noisy Label Learning Benchmark. CoRR Siqi Liang, Jintao Huang, Dun Zeng, Junyuan Hong, Jiayu Zhou, Zenglin Xu
2023	A*	`conf`	Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning. AAAI Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2023	J	`jnl`	How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts. Trans. Mach. Learn. Res. Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang
2023	A*	`conf`	International Workshop on Federated Learning for Distributed Data Mining. KDD Junyuan Hong, Zhuangdi Zhu, Lingjuan Lyu, Yang Zhou, Vishnu Naresh Boddeti, Jiayu Zhou
2023	A*	`conf`	MECTA: Memory-Economic Continual Test-Time Model Adaptation. ICLR Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger
2023	J	`jnl`	On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space. CoRR Yuyang Deng, Nidham Gazagnadou, Junyuan Hong, Mehrdad Mahdavi, Lingjuan Lyu
2023	A*	`conf`	Revisiting Data-Free Knowledge Distillation with Poisoned Teachers. ICML Junyuan Hong, Yi Zeng, Shuyang Yu, Lingjuan Lyu, Ruoxi Jia, Jiayu Zhou
2023	J	`jnl`	Revisiting Data-Free Knowledge Distillation with Poisoned Teachers. CoRR Junyuan Hong, Yi Zeng, Shuyang Yu, Lingjuan Lyu, Ruoxi Jia, Jiayu Zhou
2023	J	`jnl`	Safe and Robust Watermark Injection with a Single OoD Image. CoRR Shuyang Yu, Junyuan Hong, Haobo Zhang, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2023	A*	`conf`	Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection. ICLR Shuyang Yu, Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2023	A*	`conf`	Understanding Deep Gradient Leakage via Inversion Influence Functions. NeurIPS Haobo Zhang, Junyuan Hong, Yuyang Deng, Mehrdad Mahdavi, Jiayu Zhou
2023	J	`jnl`	Understanding Deep Gradient Leakage via Inversion Influence Functions. CoRR Haobo Zhang, Junyuan Hong, Yuyang Deng, Mehrdad Mahdavi, Jiayu Zhou
2023	J	`jnl`	Who Leaked the Model? Tracking IP Infringers in Accountable Federated Learning. CoRR Shuyang Yu, Junyuan Hong, Yi Zeng, Fei Wang, Ruoxi Jia, Jiayu Zhou
2022	—	`conf`	Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent. FAccT Junyuan Hong, Zhangyang Wang, Jiayu Zhou
2022	A*	`conf`	Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization. ICLR Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2022	J	`jnl`	Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization. CoRR Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2022	J	`jnl`	How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts. CoRR Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang
2022	A*	`conf`	Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling. NeurIPS Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger
2022	J	`jnl`	Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling. CoRR Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger
2022	A*	`conf`	Resilient and Communication Efficient Learning for Heterogeneous Federated Systems. ICML Zhuangdi Zhu, Junyuan Hong, Steve Drew, Jiayu Zhou
2022	A*	`conf`	Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. NeurIPS Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang
2022	J	`jnl`	Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. CoRR Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang
2021	A*	`conf`	Data-Free Knowledge Distillation for Heterogeneous Federated Learning. ICML Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou
2021	J	`jnl`	Data-Free Knowledge Distillation for Heterogeneous Federated Learning. CoRR Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou
2021	A*	`conf`	Federated Adversarial Debiasing for Fair and Transferable Representations. KDD Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Zhangyang Wang, Hiroko H. Dodge, Jiayu Zhou
2021	J	`jnl`	Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning. CoRR Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2021	A*	`conf`	Learning Model-Based Privacy Protection under Budget Constraints. AAAI Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
2021	J	`jnl`	On Dynamic Noise Influence in Differentially Private Learning. CoRR Junyuan Hong, Zhangyang Wang, Jiayu Zhou
2019	J	`jnl`	Short Sequence Classification Through Discriminable Linear Dynamical System. IEEE Trans. Neural Networks Learn. Syst. Yang Li, Junyuan Hong, Huanhuan Chen
2019	J	`jnl`	Variant Grassmann Manifolds: A Representation Augmentation Method for Action Recognition. ACM Trans. Knowl. Discov. Data Junyuan Hong, Yang Li, Huanhuan Chen
2018	A*	`conf`	Disturbance Grassmann Kernels for Subspace-Based Learning. KDD Junyuan Hong, Huanhuan Chen, Feng Lin
2018	J	`jnl`	Disturbance Grassmann Kernels for Subspace-Based Learning. CoRR Junyuan Hong, Huanhuan Chen, Feng Lin
2016	—	`conf`	Sequential Data Classification in the Space of Liquid State Machines. ECML/PKDD (1) Yang Li, Junyuan Hong, Huanhuan Chen