Expertini Research Research

Browse Research Papers

64,528+ open-access research outputs.

โœ• Clear
๐Ÿ” memory
Showing 64528 results for "memory"
Physics Preprint PDF DOI

Geometric memory in incomplete phase transitions across dimensions

F. Tolea, M. Tolea ยท 2026

We model a direct solid-state phase transition through a nucleation-and-growth process in which plates have simple, regular shapes - squares, cubes, or square-faced lamellae - and grow homothetically โ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Non-Gaussian hydrodynamic fluctuations in an expanding relativistic fluid

Gokce Basar, Shuo Song ยท 2026

We consider non-equilibrium evolution of non-Gaussian fluctuations in a hydrodynamic system undergoing a boost-invariant expansion described by Bjorken flow. We derive the evolution equations for two-โ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

On the proposed concept of mechanical phasons in Ni-Mn-Ga modulated martensite

Petr Sedlak, Tomas Grabec, Hanus Seiner (Institute of Thermomechanics, Czech Academy of Sciences, Prague) ยท 2026

We discuss modulation phasons as a possible source of unusual elastic behavior of five-layer modulated (10\,M) martensite of the Ni-Mn-Ga shape memory alloy. This material exhibits anomalous macroscopโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering

Xupeng Chen, Binbin Shi, Chenqian Le, Jiaqi Zhang, Kewen Wang, Ran Gong, Jinhan Zhang, Chihang Wang ยท 2026

Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of โ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Contextual Agentic Memory is a Memo, Not True Memory

Binyan Xu, Xilin Dai, Kehuan Zhang ยท 2026

Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookupโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory

Yuyang Li, Yime He, Zeyu Zhang, Dong Gong ยท 2026

Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing iterative methods refine โ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Energy efficiency of a GPU-based computing system for High Energy Physics experiments

Jiahui Zhuo, Arantza Oyanguren, Alvaro Fernandez Casani, Luca Fiorini, Valerii Kholoimov ยท 2026

In this paper we introduce the energy efficiency as a new metric for evaluating both hardware platforms based on Graphic Processor Units (GPU), and algorithm optimisations at High Energy Physics (HEP)โ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Towards All-Day Perception for Off-Road Driving: A Large-Scale Multispectral Dataset and Comprehensive Benchmark

Shuo Wang, Jilin Mei, Wenfei Guan, Shuai Wang, Yan Xing, Chen Min, Yu Hu ยท 2026

Off-road nighttime autonomous driving suffers from unreliable visible-light perception, making infrared modality crucial for accurate freespace detection. However, progress remains limited due to the โ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

VitaLLM: A Versatile, Ultra-Compact Ternary LLM Accelerator with Dependency-Aware Scheduling

Zi-Wei Lin, Tian-Sheuan Chang ยท 2026

Deploying Large Language Models (LLMs) on resource-constrained edge devices faces critical bottlenecks in memory bandwidth and power consumption. While ternary quantization (e.g., BitNet b1.58) signifโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Leading Across the Spectrum of Human-AI Relationships: A Conceptual Framework for Increasingly Heterogeneous Teams

Alejandro R. Jadad ยท 2026

What shapes a consequential decision when human and artificial intelligence work on it together? The answer is becoming harder to see. A decision may look human-led after AI has set the frame, or appeโ€ฆ

Read Paper โ†’
Computer Science Preprint PDF DOI

RCW-CIM: A Digital CIM-based LLM Accelerator with Read-Compute/Write

Yan-Cheng Guo, Tian-Sheuan Chang, Jian-Wei Su ยท 2026

Digital computing-in-memory (DCIM) has emerged as a promising solution for large language model (LLM) acceleration by minimizing data transfers between external DRAM and on-chip accelerators while maiโ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

Ultrafast Sliding Ferroelectric Switching in Bilayer Hexagonal Boron Nitride Revealed by Deep Learning Molecular Dynamics

Yinan Wang, Poyen Chen, Teruyasu Mizoguchi ยท 2026

Sliding ferroelectricity in bilayer hexagonal boron nitride (h-BN) offers compelling prospects for next-generation non-volatile memory, yet the atomistic dynamics of electric-field-driven polarizationโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Mechanized Foundations of Structural Governance: Machine-Checked Proofs for Governed Intelligence

Alan L. McCann ยท 2026

We present five results in the theory of structural governance for cognitive workflow systems. Three are mechanized in Coq 8.19 using the Interaction Trees library with parameterized coinduction; two โ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents

Mehmet Iscan ยท 2026

Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved mโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models

Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter, Yuxiang Zhou, Maria Liakata, Nikolaos Aletras ยท 2026

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. Howeveโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Remaining Useful Life Estimation for Turbofan Engines: A Comparative Study of Classical, CNN, and LSTM Approaches

Astitva Goel, Samarth Galchar, Sumit Kanu ยท 2026

Remaining Useful Life (RUL) estimation is a critical component of Prognostics and Health Management (PHM), enabling proactive maintenance scheduling and reducing unplanned failures in industrial equipโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction

Yuxuan Huang, Yihang Chen, Zhiyuan He, Yuxiang Chen, Ka Yiu Lee, Huichi Zhou, Weilin Luo, Meng Fang, Jun Wang ยท 2026

Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on โ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations

Timothy Flavin, Sandip Sen ยท 2026

Reinforcement Learning (RL) algorithms exhibit high sample complexity, particularly when applied to Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). As a response, projects sโ€ฆ

Read Paper โ†’
AI & Data Science Preprint PDF DOI

Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics

Haiyu Yang, Miel Hostens ยท 2026

Foundation-model pipelines for individual-level livestock monitoring -- combining open-vocabulary detection, promptable video segmentation, and self-supervised visual embeddings -- have raised the accโ€ฆ

Read Paper โ†’
Physics Preprint PDF DOI

First-Principles Thermodynamic Analysis of Ternary Chalcogenide Phase Change Materials

Felix Adams, Ichiro Takeuchi, Carlos Rios Ocampo, Yifei Mo ยท 2026

Chalcogenide phase-change materials (PCMs) are important for nonvolatile memory and reconfigurable photonic technologies. The GeTe-Sb2Te3 mixture system, commonly referred to as GST, is the most well-โ€ฆ

Read Paper โ†’
โ† Prev Page 2 of 3227 Next โ†’