相关论文: Modelling Expert Cognition Beyond Behaviour: Towar…

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

Objective: Decoding visual information from electroencephalography (EEG) is an important problem in neuroscience and brain-computer interface (BCI) research. Existing methods are largely restricted to natural images and categorical…

The rapid development and adoption of Generative AI (GAI) technology in the form of chatbots such as ChatGPT and Claude has greatly increased interest in agentic machines. This paper introduces the Autonomous Cognitive Entity (ACE) model, a…

Consciousness has been hypothesized to operate as a global workspace, which accesses and integrates multimodal information in a unified manner, supports expectation violation monitoring and reduction, and the motivation, programming and…

In-context learning (ICL) achieves remarkable performance in various domains such as knowledge acquisition, commonsense reasoning, and semantic understanding. However, its performance significantly deteriorates for emotion detection tasks,…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

Concept bottleneck models (CBMs), which predict human-interpretable concepts (e.g., nucleus shapes in cell images) before predicting the final output (e.g., cell type), provide insights into the decision-making processes of the model.…

The capability of Unified Multimodal Models (UMMs) to apply world knowledge across diverse tasks remains a critical, unresolved challenge. Existing benchmarks fall short, offering only siloed, single-task evaluations with limited diagnostic…

This paper challenges a prevailing epistemological assumption in End-to-End Autonomous Driving: that high-performance planning necessitates high-fidelity world reconstruction. Inspired by cognitive science, we propose the Mental Bayesian…

Concept-Based Models (CBMs) are a class of deep learning models that provide interpretability by explaining predictions through high-level concepts. These models first predict concepts and then use them to perform a downstream task.…

The Human Cognitive Simulation Framework proposes a governed cognitive AI architecture designed to improve personalization, adaptability, and long-term coherence in human AI interaction. The framework integrates short-term memory…

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features…

This position paper presents a theoretical framework for enhancing explainable artificial intelligence (xAI) through emergent communication (EmCom), focusing on creating a causal understanding of AI model outputs. We explore the novel…

Current embodied agents are often limited to passive instruction-following or reactive need-satisfaction, lacking a stable, high-order value framework essential for long-term, self-directed behavior and resolving motivational conflicts. We…

Cross-subject variability in EEG degrades performance of current deep learning models, limiting the development of brain-computer interface (BCI). This paper proposes ISAM-MTL, which is a multi-task learning (MTL) EEG classification model…

The massive growth in the utilization of edge AI has made the applications of machine learning models ubiquitous in different domains. Despite the computation and communication efficiency of these systems, due to limited computation…

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…

The Intelligent System of Emergent Knowledge (ISEK) establishes a decentralized network where human and artificial intelligence agents collaborate as peers, forming a self-organizing cognitive ecosystem. Built on Web3 infrastructure, ISEK…