Junlin Wu - RankMe

23 papers A* 8Journal 12Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Conformal Reachability for Safe Control in Unknown Environments. CoRR Xinhang Ma, Junlin Wu, Yiannis Kantaros, Yevgeniy Vorobeychik
2026	A*	`conf`	Learning Vision-Based Neural Network Controllers with Semi-Probabilistic Safety Guarantees. AAAI Xinhang Ma, Junlin Wu, Hussein Sibai, Yiannis Kantaros, Yevgeniy Vorobeychik
2025	J	`jnl`	Learning Vision-Based Neural Network Controllers with Semi-Probabilistic Safety Guarantees. CoRR Xinhang Ma, Junlin Wu, Hussein Sibai, Yiannis Kantaros, Yevgeniy Vorobeychik
2025	A*	`conf`	Preference Poisoning Attacks on Reward Model Learning. SP Junlin Wu, Jiongxiao Wang, Chaowei Xiao, Chenguang Wang, Ning Zhang, Yevgeniy Vorobeychik
2024	A*	`conf`	Axioms for AI Alignment from Human Feedback. NeurIPS Luise Ge, Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu
2024	J	`jnl`	Axioms for AI Alignment from Human Feedback. CoRR Luise Ge, Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu
2024	—	`conf`	Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks. SP (Workshops) Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik
2024	J	`jnl`	Preference Poisoning Attacks on Reward Model Learning. CoRR Junlin Wu, Jiongxiao Wang, Chaowei Xiao, Chenguang Wang, Ning Zhang, Yevgeniy Vorobeychik
2024	—	`conf`	RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models. ACL (1) Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao
2024	A*	`conf`	Verified Safe Reinforcement Learning for Neural Network Dynamic Models. NeurIPS Junlin Wu, Huan Zhang, Yevgeniy Vorobeychik
2024	J	`jnl`	Verified Safe Reinforcement Learning for Neural Network Dynamic Models. CoRR Junlin Wu, Huan Zhang, Yevgeniy Vorobeychik
2023	A*	`conf`	Exact Verification of ReLU Neural Control Barrier Functions. NeurIPS Hongchao Zhang, Junlin Wu, Yevgeniy Vorobeychik, Andrew Clark
2023	J	`jnl`	Exact Verification of ReLU Neural Control Barrier Functions. CoRR Hongchao Zhang, Junlin Wu, Yevgeniy Vorobeychik, Andrew Clark
2023	A*	`conf`	Neural Lyapunov Control for Discrete-Time Systems. NeurIPS Junlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy Vorobeychik
2023	J	`jnl`	Neural Lyapunov Control for Discrete-Time Systems. CoRR Junlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy Vorobeychik
2023	J	`jnl`	On the Exploitability of Reinforcement Learning with Human Feedback for Large Language Models. CoRR Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao
2022	J	`jnl`	Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attacks. CoRR Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik
2022	A*	`conf`	Manipulating Elections by Changing Voter Perceptions. IJCAI Junlin Wu, Andrew Estornell, Lecheng Kong, Yevgeniy Vorobeychik
2022	J	`jnl`	Manipulating Elections by Changing Voter Perceptions. CoRR Junlin Wu, Andrew Estornell, Lecheng Kong, Yevgeniy Vorobeychik
2022	A*	`conf`	Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum. ICML Junlin Wu, Yevgeniy Vorobeychik
2022	J	`jnl`	Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum. CoRR Junlin Wu, Yevgeniy Vorobeychik
2021	—	`conf`	Learning Generative Deception Strategies in Combinatorial Masking Games. GameSec Junlin Wu, Charles A. Kamhoua, Murat Kantarcioglu, Yevgeniy Vorobeychik
2021	J	`jnl`	Learning Generative Deception Strategies in Combinatorial Masking Games. CoRR Junlin Wu, Charles A. Kamhoua, Murat Kantarcioglu, Yevgeniy Vorobeychik