Related papers: Multiscale Information Storage of Linear Long-Rang…
Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, these systems are usually evaluated in terms of robustness: whether performance is…
Learning-based control has attracted significant attention in recent years, especially for plants that are difficult to model based on first-principles. A key issue in learning-based control is how to make efficient use of data as the…
Determining a process-structure-property relationship is the holy grail of materials science, where both computational prediction in the forward direction and materials design in the inverse direction are essential. Problems in materials…
The penetration of renewable energies requires additional storages to deal with intermittency. Accordingly, there is growing interest in evaluating the opportunity cost (usage value) associated with stored energy in large storages, a cost…
Flexibility at hardware level is the main driving force behind adaptive systems whose aim is to realise microarhitecture deconfiguration 'online'. This feature allows the software/hardware stack to tolerate drastic changes of the workload…
The computational properties of neural systems are often thought to be implemented in terms of their network dynamics. Hence, recovering the system dynamics from experimentally observed neuronal time series, like multiple single-unit (MSU)…
Advances in materials science have led to physical instantiations of self-assembled networks of memristive devices and demonstrations of their computational capability through reservoir computing. Reservoir computing is an approach that…
Retrieval-Augmented Generation (RAG) has shown significant improvements in various natural language processing tasks by integrating the strengths of large language models (LLMs) and external knowledge databases. However, RAG introduces long…
While the volume of electronic health records (EHR) data continues to grow, it remains rare for hospital systems to capture dense physiological data streams, even in the data-rich intensive care unit setting. Instead, typical EHR records…
In a sequential decision-making problem, the information structure is the description of how events in the system occurring at different points in time affect each other. Classical models of reinforcement learning (e.g., MDPs, POMDPs)…
Purpose. Athlete monitoring is constrained by small cohorts, heterogeneous biomarker scales, limited feasibility of repeated sampling, and the lack of reliable injury ground truth. These limitations reduce the interpretability and utility…
We propose a unified theoretical framework for quantifying spatio-temporal interactions in a stochastic dynamical system based on information geometry. In the proposed framework, the degree of interactions is quantified by the divergence…
The rapid increase in textual information means we need more efficient methods to sift through, organize, and understand it all. While retrieval-augmented generation (RAG) models excel in accessing information from large document…
With the increasing complexity and size of capacity expansion models, temporal aggregation has emerged as a common method to improve computational tractability. However, this approach inherently complicates the inclusion of long-duration…
Large language models are increasingly deployed as research agents for deep search and long-horizon information seeking, yet their performance often degrades as interaction histories grow. This degradation, known as context rot, reflects a…
We study dynamical reversibility in stationary stochastic processes from an information theoretic perspective. Extending earlier work on the reversibility of Markov chains, we focus on finitary processes with arbitrarily long conditional…
Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…
Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…
Relaxed retention (or volatile) spin-transfer torque RAM (STT-RAM) has been widely studied as a way to reduce STT-RAM's write energy and latency overheads. Given a relaxed retention time STT-RAM level one (L1) cache, we analyze the impacts…
Numerical modeling of different structural materials that have highly nonlinear behaviors has always been a challenging problem in engineering disciplines. Experimental data is commonly used to characterize this behavior. This study aims to…