arXiv subjects

Subhabrata Das

Publications and source records attributed to Subhabrata Das.

6 recordsLinked to original sources

arXiv2026

A self-compliant selector-free memory with functional bismuth ferrite

In-memory computing requires selector-free operation, low variability, and stable multilevel switching, all of which remain challenging to achieve in a single system. Here, we demonstrate a robust selector-free memory based on a multiferroic BiFeO3 that combines self-compliance with stable bipolar switching, high yield, long endurance, and extended retention. We observe that BiFeO3 memristive crossbar arrays become self-compliant through a naturally formed TiOx interfacial layer, enabling forming-free bipolar switching without external selector devices, addressing major bottlenecks that have limited the practical deployment of resistive memories. The array delivers stable bipolar switching with a 97% device yield, endurance beyond 105 cycles, and data retention exceeding 105 s with low cycle-to-cycle and device-to-device variability. In addition, the devices exhibit 16 well-separated conductance states, enabling 4-bit multilevel operation via precise pulse-controlled programming for digit visualization in edge applications. Noise measurements reveal predominantly 1/f-type behavior with minimal random telegraph noise, indicating robust conductance stability across the programmable window. These results establish BiFeO3 as a practical materials platform for multibit, selector-free crossbar memories offering high reliability, making it well-suited for scalable computing architectures based on functional materials.

cond-mat.mes-hall↗

arXiv2026

Hybrid LLM-based Intelligent Framework for Robot Task Scheduling

This study introduces intelligent frameworks that use Large Language Models (LLMs) to improve task scheduling for construction robots. The LLM is fed with key data about the desired task, such as agent action abilities, and the desired end goal to be achieved. A well-balanced allocation strategy is developed, optimizing both time efficiency and resource utilization. Our system utilizes a Natural Language Processing interface to streamline communication with construction professionals and adapt in real-time to unexpected site conditions. We concurrently use two LLM agents, specifically generator (GPT-4) and supervisor (Gemma 3/Llama 4/Mistral 7b) LLM agents to provide a more precise task schedule. We evaluate the proposed methodology using a straightforward scenario and provide metric scores to prove the efficacy of the frameworks. Our results highlight that the implementation of LLMs is crucial in construction operational tasks including robots.

cs.RO↗

arXiv2026

Liquid Neural Network Models for Natural Gas Spot Price Time-Series Forecasting

Natural gas is undoubtedly an essential component of the global energy system. Accurate short-term forecasting of natural gas price is challenging due to pronounced volatility driven by seasonal demand patterns, geopolitical developments, and shifting macroeconomic conditions. The nonlinear dynamics and frequent regime changes can limit the effectiveness of traditional time-series models. In this study, we explore the use of Liquid Neural Networks (LNNs) for short-horizon forecasting of the Henry Hub spot price, a primary benchmark for pricing. LNNs are designed to adapt continuously to evolving temporal patterns through dynamic internal state updates, making them well suited for nonstationary price behavior. By improving forecast accuracy in volatile market conditions, this work aims to reduce uncertainty and enhance decision support across energy trading and power market applications.

cs.LG↗

arXiv2026

Quantum Resistance in Multilayer Graphene-BiFeO3 Memristor for Brain-Inspired Computing

In the era of big data and the Internet of Things, quantum-level control of conductance states offers a promising route toward high-density data storage and brain-inspired neuromorphic computing. Although quantum conductance (QC) phenomena have been demonstrated in various metal oxide memristors, achieving reliable and precise control over quantized states remains in its infancy. Here, we demonstrate bidirectional quantum conductance states in multifunctional BiFeO3 (BFO) perovskite memristors integrated with multilayer-graphene contacts, enabling higher-order tunability and revealing the potential of perovskite-2D heterostructures for quantum-engineered memory and computing devices. XPS analysis provides detailed insights into oxygen vacancy dynamics in BFO, whereas first-principles density functional theory calculations clearly reveal a strong localized electric field at the graphene-BFO interface. Our devices exhibit current-controlled higher-order QC transitions facilitated by quantum point contact formation, giving rise to quantized conductance states during both SET and RESET processes. Time-lag correlation maps quantify the stochastic evolution of QC states under dynamic voltage-pulse tuning schemes. Notably, the quantized conductance states effectively emulate synaptic potentiation and depression, enabling precise weight modulation for high-accuracy image and digit recognition in convolutional neural networks. These findings establish perovskite-2D heterostructures as promising candidates for QC-driven resistive switching and demonstrate their potential for developing controllable quantum memristors.

cond-mat.mes-hall↗

arXiv2025

A Hybrid PCA-PR-Seq2Seq-Adam-LSTM Framework for Time-Series Power Outage Prediction

Accurately forecasting power outages is a complex task influenced by diverse factors such as weather conditions [1], vegetation, wildlife, and load fluctuations. These factors introduce substantial variability and noise into outage data, making reliable prediction challenging. Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN), are particularly effective for modeling nonlinear and dynamic time-series data, with proven applications in stock price forecasting [2], energy demand prediction, demand response [3], and traffic flow management [4]. This paper introduces a hybrid deep learning framework, termed PCA-PR-Seq2Seq-Adam-LSTM, that integrates Principal Component Analysis (PCA), Poisson Regression (PR), a Sequence-to-Sequence (Seq2Seq) architecture, and an Adam-optimized LSTM. PCA is employed to reduce dimensionality and stabilize data variance, while Poisson Regression effectively models discrete outage events. The Seq2Seq-Adam-LSTM component enhances temporal feature learning through efficient gradient optimization and long-term dependency capture. The framework is evaluated using real-world outage records from Michigan, and results indicate that the proposed approach significantly improves forecasting accuracy and robustness compared to existing methods.

cs.LG↗

arXiv2024

EQUATOR: A Deterministic Framework for Evaluating LLM Reasoning with Open-Ended Questions. # v1.0.0-beta

Despite the remarkable coherence of Large Language Models (LLMs), existing evaluation methods often suffer from fluency bias and rely heavily on multiple-choice formats, making it difficult to assess factual accuracy and complex reasoning effectively. LLMs thus frequently generate factually inaccurate responses, especially in complex reasoning tasks, highlighting two prominent challenges: (1) the inadequacy of existing methods to evaluate reasoning and factual accuracy effectively, and (2) the reliance on human evaluators for nuanced judgment, as illustrated by Williams and Huckle (2024)[1], who found manual grading indispensable despite automated grading advancements. To address evaluation gaps in open-ended reasoning tasks, we introduce the EQUATOR Evaluator (Evaluation of Question Answering Thoroughness in Open-ended Reasoning). This framework combines deterministic scoring with a focus on factual accuracy and robust reasoning assessment. Using a vector database, EQUATOR pairs open-ended questions with human-evaluated answers, enabling more precise and scalable evaluations. In practice, EQUATOR significantly reduces reliance on human evaluators for scoring and improves scalability compared to Williams and Huckle's (2004)[1] methods. Our results demonstrate that this framework significantly outperforms traditional multiple-choice evaluations while maintaining high accuracy standards. Additionally, we introduce an automated evaluation process leveraging smaller, locally hosted LLMs. We used LLaMA 3.2B, running on the Ollama binaries to streamline our assessments. This work establishes a new paradigm for evaluating LLM performance, emphasizing factual accuracy and reasoning ability, and provides a robust methodological foundation for future research.

cs.CL↗