Related papers: MiA-Signature: Approximating Global Activation for…
Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language…
Long-context LLMs and Retrieval-Augmented Generation (RAG) systems process information passively, deferring state tracking, contradiction resolution, and evidence aggregation to query time, which becomes brittle under ultra long streams…
Language models (LMs) have been used in cognitive modeling as well as engineering studies -- they compute information-theoretic complexity metrics that simulate humans' cognitive load during reading. This study highlights a limitation of…
Large language models (LLMs) have achieved remarkable success in text-based tasks but often struggle to provide actionable guidance in real-world physical environments. This is because of their inability to recognize their limited…
While Large Language Models (LLMs) demonstrate strong performance across domains, their long-context capabilities are limited by transient neural activations causing information decay and unstructured feed-forward network (FFN) weights…
Remote memory access (RMA) is an emerging high-performance programming model that uses RDMA hardware directly. Yet, accessing remote memories cannot invoke activities at the target which complicates implementation and limits performance of…
The context window of large language models has been extended to 128k tokens or more. However, language models still suffer from position bias and have difficulty in accessing and using the middle part of the context due to the lack of…
Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine reasoning capabilities, such as…
We adapt an information theory analysis of interacting cognitive biological and social modules to the problem of the global neuronal workspace, the current standard neuroscience picture of consciousness. Tunable punctuation emerges in a…
We propose a novel framework for persona-based language model system, motivated by the need for personalized AI agents that adapt to individual user preferences. In our approach, the agent embodies the user's "persona" (e.g. user profile or…
Human reasoning can be understood as a cooperation between the intuitive, associative "System-1" and the deliberative, logical "System-2". For existing System-1-like methods in visual activity understanding, it is crucial to integrate…
While Large Language Models (LLMs) demonstrate exceptional performance in a multitude of Natural Language Processing (NLP) tasks, they encounter challenges in practical applications, including issues with hallucinations, inadequate…
Deciphering the human visual experience through brain activities captured by fMRI represents a compelling and cutting-edge challenge in the field of neuroscience research. Compared to merely predicting the viewed image itself, decoding…
The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…
Nowadays, a huge number of images are available. However, retrieving a required image for an ordinary user is a challenging task in computer vision systems. During the past two decades, many types of research have been introduced to improve…
The idea that information-processing systems operate near criticality to enhance computational performance is supported by scaling signatures in brain activity. However, external signals raise the question of whether this behavior is…
Current interactive systems with natural language interfaces lack the ability to understand a complex information-seeking request which expresses several implicit constraints at once, and there is no prior information about user preferences…
Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…
Image captioning is a research hotspot where encoder-decoder models combining convolutional neural network (CNN) and long short-term memory (LSTM) achieve promising results. Despite significant progress, these models generate sentences…
Large Language Models show promise in emotion understanding, social reasoning, and empathy, yet they struggle with psychologically grounded tasks that require inferring implicit mental states in context-rich, ambiguous settings. These…