no code implementations • 2 Feb 2024 • Junlin Wu, Jiongxiao Wang, Chaowei Xiao, Chenguang Wang, Ning Zhang, Yevgeniy Vorobeychik
In addition, we observe that the simpler and more scalable rank-by-distance approaches are often competitive with the best, and on occasion significantly outperform gradient-based methods.
no code implementations • 16 Nov 2023 • Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao
Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignment.
1 code implementation • NeurIPS 2023 • Junlin Wu, Andrew Clark, Yiannis Kantaros, Yevgeniy Vorobeychik
However, finding Lyapunov functions for general nonlinear systems is a challenging task.
no code implementations • 28 Dec 2022 • Junlin Wu, Hussein Sibai, Yevgeniy Vorobeychik
Our experiments demonstrate both the efficacy of the proposed approach for certifying safety in adversarial environments, and the value of the PSRL framework coupled with adversarial training in improving certified safety while preserving high nominal reward and high-quality predictions of true state.
1 code implementation • 21 Jun 2022 • Junlin Wu, Yevgeniy Vorobeychik
Despite considerable advances in deep reinforcement learning, it has been shown to be highly vulnerable to adversarial perturbations to state observations.
no code implementations • 23 Sep 2021 • Junlin Wu, Charles Kamhoua, Murat Kantarcioglu, Yevgeniy Vorobeychik
Next, we present a novel highly scalable approach for approximately solving such games by representing the strategies of both players as neural networks.
1 code implementation • EMNLP 2018 • Elvis Saravia, Hsien-Chi Toby Liu, Yen-Hao Huang, Junlin Wu, Yi-Shin Chen
Emotions are expressed in nuanced ways, which varies by collective or individual experiences, knowledge, and beliefs.