1 code implementation • 19 Mar 2024 • Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, QIngwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Dongmei Zhang
The challenge is that information entropy may be a suboptimal compression metric: (i) it only leverages unidirectional context and may fail to capture all essential information needed for prompt compression; (ii) it is not aligned with the prompt compression objective.
no code implementations • 29 Feb 2024 • Huisheng Wang, Zhanjiang Chen, H. Vicky Zhao
The Message-Enhanced DeGroot model, combining the Bounded Brownian Message model with the traditional DeGroot model, quantitatively describes the evolution of agents' opinions under the influence of messages.
no code implementations • 14 Jan 2024 • Huisheng Wang, H. Vicky Zhao
Furthermore, to quantify the preference for their rational decision over that of the other agent, we introduce the agent's investment opinion.
1 code implementation • 4 Nov 2023 • Zhuoshi Pan, Yuguang Yao, Gaowen Liu, Bingquan Shen, H. Vicky Zhao, Ramana Rao Kompella, Sijia Liu
We show that this latter insight can be used to enhance the detection of backdoor-poisoned training data.
no code implementations • 28 Aug 2023 • Wenxiang Dong, Zhanjiang Chen, H. Vicky Zhao
Epidemics such as COVID-19 pose serious threats to public health and our society, and it is critical to investigate effective methods to control the spread of epidemics over networks.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 10 Mar 2023 • Qingming Li, H. Vicky Zhao
Choice problems refer to selecting the best choices from several items, and learning users' preferences in choice problems is of great significance in understanding the decision making mechanisms and providing personalized services.
no code implementations • 9 Mar 2023 • Qingming Li, H. Vicky Zhao
In this work, we specifically focus on two commonly observed biases: projection bias and the reference-point effect.