Literature Review

[This review is intended solely for my personal learning] Paper Info arXiv: 2210.00864v1 Title: quEEGNet: Quantum AI for Biosignal Processing Authors: Toshiaki Koike-Akino, Ye Wang Prior Knowledge Biosignal Processing in Human-Machine Interfaces (HMI) Biosignals such as EEG (electroencephalogram), EMG (electromyogram), and ECoG (electrocorticogram) are fundamental to developing brain-computer interfaces (BCI) and HMIs. However, biosignals are subject to high variability and noise, requiring robust machine-learning models for feature extraction and classification. ...

[This review is intended solely for my personal learning] Paper Info DOI: 10.1111/tops.12404 Title: The Flatland Fallacy: Moving Beyond Low–Dimensional Thinking Authors: Eshin Jolly, Luke J. Chang Prior Knowledge Psychological and cognitive sciences have long relied on simplified, low-dimensional models to explain complex human behavior. While these models provide theoretical clarity and empirical tractability, they often fail to capture the full intricacy of psychological phenomena. The reliance on two-factor or low-dimensional frameworks—such as dual-process theories of cognition—raises concerns about scientific oversimplification. ...

[This review is intended solely for my personal learning] Paper Info DOI: 10.1177/17456916231200177 Title: The Emerging Science of Interacting Minds Authors: Thalia Wheatley, Mark A. Thornton, Arjen Stolk, and Luke J. Chang Prior Knowledge Historically, psychology has focused on the individual, often isolating cognitive processes within a single brain. However, social interaction is fundamental to human cognition, development, and collective behavior. While past research in social psychology and neuroscience has explored elements of interaction, methodological constraints have limited empirical studies that directly analyze interaction dynamics. ...

[This review is intended solely for my personal learning] Paper Info Title: TD-MPC2: Scalable, Robust World Models for Continuous Control Authors: Nicklas Hansen, Hao Su, Xiaolong Wang Conference: ICLR 2024 arXiv: 2310.16828 Prior Knowledge Model-Based Reinforcement Learning (MBRL): Uses an internal model of the environment to plan and optimize actions rather than learning policies from direct interaction alone. Temporal Difference Learning: A method in RL that estimates the value function iteratively using bootstrapped learning. Model Predictive Control (MPC): An optimization framework for selecting actions over a finite horizon using a learned world model. TD-MPC: A prior algorithm that performs local trajectory optimization in the latent space of an implicit world model but lacks scalability and robustness. Goal The authors propose TD-MPC2, an extension of the TD-MPC framework, designed to scale reinforcement learning to large, uncurated datasets and generalize across multiple continuous control tasks. The key aims are: ...

[This review is intended solely for my personal learning] Paper Info arXiv: 2405.02814 Title: NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli Authors: Xu Wang, Cheng Li, Yi Chang, Jindong Wang, Yuan Wu Prior Knowledge Emotion and Cognition in AI: Previous research has shown that positive emotional stimuli improve LLM performance, raising the question of whether negative emotional stimuli can also have an impact. Psychological Theories: The study draws on Cognitive Dissonance Theory, Social Comparison Theory, and Stress and Coping Theory to design negative emotional prompts that may influence LLM responses. Goal To explore whether negative emotional stimuli, integrated into prompts, can enhance the performance of LLMs across various NLP tasks. The study introduces NegativePrompt, a novel prompting technique that applies negative emotional cues to improve LLM output quality. ...