arXiv subjects

Shivang Agarwal

Publications and source records attributed to Shivang Agarwal.

17 recordsLinked to original sources

arXiv2026

AQVolt26: High-Temperature r$^2$SCAN Halide Dataset for Universal ML Potentials and Solid-State Batteries

The demand for safe, high-energy-density batteries has spotlighted halide solid-state electrolytes, which offer the potential for enhanced ionic mobility, electrochemical stability, and interfacial deformability. Accelerating their discovery requires extensive molecular dynamics, which has been increasingly enabled by universal machine learning interatomic potentials trained on foundational datasets. However, the dynamic softness of halides poses a stringent test of whether general-purpose models can reliably replace first-principles calculations under the highly distorted, elevated-temperature regimes necessary to probe ion transport. Here, we present AQVolt26, a dataset of 322,656 r$^2$SCAN single-point calculations for lithium halides, generated via high-temperature configurational sampling across $\sim$5K structures. We demonstrate that foundational datasets provide a strong baseline for stable halide chemistries and transfer local forces well, however absolute energy predictions degrade in distorted higher-temperature regimes. Co-training with AQVolt26 resolves this blind spot. Furthermore, incorporating Materials Project relaxation data improves near-equilibrium performance but degrades extreme-strain robustness without enhancing high-temperature force accuracy. These results demonstrate that domain-specific configurational sampling is essential for the reliable dynamic screening of halide electrolytes. Furthermore, our findings suggest that while foundational models provide a robust base, they are most effective for dynamically soft solid-state chemistries when augmented with targeted, high-temperature data. Finally, we show that near-equilibrium relaxation data serves as a task-specific complement rather than a universally beneficial addition.

cond-mat.mtrl-sci↗

arXiv2026

Electronic structure prediction of medium and high entropy alloys across composition space

We propose machine learning (ML) models to predict the electron density -- the fundamental unknown of a material's ground state -- across the composition space of concentrated alloys. From this, other physical properties can be inferred, enabling accelerated exploration. A significant challenge is that the number of sampled compositions and descriptors required to accurately predict fields like the electron density increases rapidly with species. To address this, we employ Bayesian Active Learning (AL), which minimizes training data requirements by leveraging uncertainty quantification capabilities of Bayesian Neural Networks. Compared to strategic tessellation of the composition space, Bayesian-AL reduces the number of training data points by a factor of 2.5 for ternary (SiGeSn) and 1.7 for quaternary (CrFeCoNi) systems. We also introduce easy-to-optimize, body-attached-frame descriptors, which respect physical symmetries and maintain approximately the same descriptor-vector size as alloy elements increase. Our ML models demonstrate high accuracy and generalizability in predicting both electron density and energy across composition space.

cond-mat.mtrl-sci↗

arXiv2025

AQCat25: Unlocking spin-aware, high-fidelity machine learning potentials for heterogeneous catalysis

Large-scale datasets have enabled highly accurate machine learning interatomic potentials (MLIPs) for general-purpose heterogeneous catalysis modeling. There are, however, some limitations in what can be treated with these potentials because of gaps in the underlying training data. To extend these capabilities, we introduce AQCat25, a complementary dataset of 13.5 million density functional theory (DFT) single point calculations designed to improve the treatment of systems where spin polarization and/or higher fidelity are critical. We also investigate methodologies for integrating new datasets, such as AQCat25, with the broader Open Catalyst 2020 (OC20) dataset to create spin-aware models without sacrificing generalizability. We find that directly tuning a general model on AQCat25 leads to catastrophic forgetting of the original dataset's knowledge. Conversely, joint training strategies prove effective for improving accuracy on the new data without sacrificing general performance. This joint approach introduces a challenge, as the model must learn from a dataset containing both mixed-fidelity calculations and mixed-physics (spin-polarized vs. unpolarized). We show that explicitly conditioning the model on this system-specific metadata, for example by using Feature-wise Linear Modulation (FiLM), successfully addresses this challenge and further enhances model accuracy. Ultimately, our work establishes an effective protocol for bridging DFT fidelity domains to advance the predictive power of foundational models in catalysis.

cond-mat.mtrl-sci↗

arXiv2025

Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires retraining from scratch or redesigning data pipelines, recent advances in machine unlearning provide a promising alternative for post-hoc model correction. In this work, we investigate \textit{Bias-Aware Machine Unlearning}, a paradigm that selectively removes biased samples or feature representations to mitigate diverse forms of bias in vision models. Building on privacy-preserving unlearning techniques, we evaluate various strategies including Gradient Ascent, LoRA, and Teacher-Student distillation. Through empirical analysis on three benchmark datasets, CUB-200-2011 (pose bias), CIFAR-10 (synthetic patch bias), and CelebA (gender bias in smile detection), we demonstrate that post-hoc unlearning can substantially reduce subgroup disparities, with improvements in demographic parity of up to \textbf{94.86\%} on CUB-200, \textbf{30.28\%} on CIFAR-10, and \textbf{97.37\%} on CelebA. These gains are achieved with minimal accuracy loss and with methods scoring an average of 0.62 across the 3 settings on the joint evaluation of utility, fairness, quality, and privacy. Our findings establish machine unlearning as a practical framework for enhancing fairness in deployed vision systems without necessitating full retraining.

cs.CV↗

arXiv2025

Early-Cycle Internal Impedance Enables ML-Based Battery Cycle Life Predictions Across Manufacturers

Predicting the end-of-life (EOL) of lithium-ion batteries across different manufacturers presents significant challenges due to variations in electrode materials, manufacturing processes, cell formats, and a lack of generally available data. Methods that construct features solely on voltage-capacity profile data typically fail to generalize across cell chemistries. This study introduces a methodology that combines traditional voltage-capacity features with Direct Current Internal Resistance (DCIR) measurements, enabling more accurate and generalizable EOL predictions. The use of early-cycle DCIR data captures critical degradation mechanisms related to internal resistance growth, enhancing model robustness. Models are shown to successfully predict the number of cycles to EOL for unseen manufacturers of varied electrode composition with a mean absolute error (MAE) of 150 cycles. This cross-manufacturer generalizability reduces the need for extensive new data collection and retraining, enabling manufacturers to optimize new battery designs using existing datasets. Additionally, a novel DCIR-compatible dataset is released as part of ongoing efforts to enrich the growing ecosystem of cycling data and accelerate battery materials development.

cs.LG↗

arXiv2024

Electronic Structure Prediction of Multi-million Atom Systems Through Uncertainty Quantification Enabled Transfer Learning

The ground state electron density -- obtainable using Kohn-Sham Density Functional Theory (KS-DFT) simulations -- contains a wealth of material information, making its prediction via machine learning (ML) models attractive. However, the computational expense of KS-DFT scales cubically with system size which tends to stymie training data generation, making it difficult to develop quantifiably accurate ML models that are applicable across many scales and system configurations. Here, we address this fundamental challenge by employing transfer learning to leverage the multi-scale nature of the training data, while comprehensively sampling system configurations using thermalization. Our ML models are less reliant on heuristics, and being based on Bayesian neural networks, enable uncertainty quantification. We show that our models incur significantly lower data generation costs while allowing confident -- and when verifiable, accurate -- predictions for a wide variety of bulk systems well beyond training, including systems with defects, different alloy compositions, and at unprecedented, multi-million-atom scales. Moreover, such predictions can be carried out using only modest computational resources.

cond-mat.mtrl-sci↗

arXiv2023

Carbon Kagome Nanotubes -- quasi-one-dimensional nanostructures with flat bands

We introduce carbon Kagome nanotubes (CKNTs) -- a new allotrope of carbon formed by rolling up sheets of Kagome graphene, and investigate the properties of this material using first principles calculations. Based on the direction of rolling, we identify two principal varieties of CKNTs -- armchair and zigzag, and find that the bending stiffness associated with rolling Kagome graphene into either type of CKNT is about a third of that associated with rolling conventional graphene into carbon nanotubes (CNTs). Ab initio molecular dynamics simulations indicate that both types of CKNTs are likely to exist as stable structures at room temperature. Each CKNT explored here is metallic and features dispersionless states (i.e., flat bands) throughout its Brillouin zone, along with an associated singular peak in the electronic density of states, close to the Fermi level. We calculate the mechanical and electronic response of CKNTs to torsional and axial strains and compare against conventional CNTs. We show in particular, that upon twisting, degenerate dispersionless electronic states in CKNTs split, Dirac points and partially flat bands emerge from the quadratic band crossing point at the Fermi level, and that these features can be explained using a relatively simple tight-binding model. Overall, CKNTs appear to be unique and striking examples of realistic elemental quasi-one-dimensional (1D) materials that can potentially display fascinating collective material properties arising from the presence of strongly correlated electrons. Additionally, distorted CKNTs may provide an interesting material platform where flat band physics and chirality induced anomalous transport effects may be studied together.

cond-mat.mtrl-sci↗

arXiv2023

Entanglement and coherence in pure and doped Posner molecules

The potential role of spin in biological systems is a primary topic in quantum biology. However, much of this research focuses on electron spin. A recent hypothesis suggests that nuclear spin may be better suited to biological processes, being less sensitive to decoherence. The hypothesis details how phosphorus nuclei might be prepared in a spin-entangled state, how this entanglement is protected by assembly into calcium phosphate (Posner) molecules, and how this entanglement might modulate calcium ion production and concomitant neural activation. In this paper, we investigate the robustness of quantum effects such as coherence and entanglement in Posner molecules. We investigate how these effects are directly dependent on specific parameters such as spin-spin coupling strengths and Posner molecule symmetry. We also investigate how lithium isotope-doped Posner molecules differentially modulate quantum resources such as coherence and entanglement and whether this is a viable explanation for lithium's mechanism of action in bipolar disease. Finally, we illustrate how entanglement might possibly be preserved through the exploitation of the biological environment.

quant-ph↗

arXiv2023

Solution of the Schrodinger equation for quasi-one-dimensional materials using helical waves

We formulate and implement a spectral method for solving the Schrodinger equation, as it applies to quasi-one-dimensional materials and structures. This allows for computation of the electronic structure of important technological materials such as nanotubes (of arbitrary chirality), nanowires, nanoribbons, chiral nanoassemblies, nanosprings and nanocoils, in an accurate, efficient and systematic manner. Our work is motivated by the observation that one of the most successful methods for carrying out electronic structure calculations of bulk/crystalline systems -- the plane-wave method -- is a spectral method based on eigenfunction expansion. Our scheme avoids computationally onerous approximations involving periodic supercells often employed in conventional plane-wave calculations of quasi-one-dimensional materials, and also overcomes several limitations of other discretization strategies, e.g., those based on finite differences and atomic orbitals. We describe the setup of fast transforms to carry out discretization of the governing equations using our basis set, and the use of matrix-free iterative diagonalization to obtain the electronic eigenstates. Miscellaneous computational details, including the choice of eigensolvers, use of a preconditioning scheme, evaluation of oscillatory radial integrals and the imposition of a kinetic energy cutoff are discussed. We have implemented these strategies into a computational package called HelicES (Helical Electronic Structure). We demonstrate the utility of our method in carrying out systematic electronic structure calculations of various quasi-one-dimensional materials through numerous examples involving nanotubes, nanoribbons and nanowires. We also explore the convergence, accuracy and efficiency of our method. We anticipate that our method will find numerous applications in computational nanomechanics and materials science.

physics.comp-ph↗

arXiv2023

The Biological Qubit: Calcium Phosphate Dimers, not Trimers

The Posner molecule (calcium phosphate trimer), has been hypothesized to function as a biological quantum information processor due to its supposedly long-lived entangled $^{31}$P nuclear spin states. This hypothesis was challenged by our recent finding that the molecule lacks a well-defined rotational axis of symmetry -- an essential assumption in the proposal for Posner-mediated neural processing -- and exists as an asymmetric dynamical ensemble. Following up, we investigate here the spin dynamics of the molecule's entangled $^{31}$P nuclear spins within the asymmetric ensemble. Our simulations show that entanglement between two nuclear spins prepared in a Bell state in separate Posner molecules decays on a sub-second timescale -- much faster than previously hypothesized, and not long enough for super-cellular neuronal processing. Calcium phosphate dimers however, are found to be surprisingly resilient to decoherence and are able to preserve entangled nuclear spins for hundreds of seconds, suggesting that neural processing might occur through them instead.

quant-ph↗

arXiv2021

A Chirality-Based Quantum Leap

Chiral degrees of freedom occur in matter and in electromagnetic fields and constitute an area of research that is experiencing renewed interest driven by recent observations of the chiral-induced spin selectivity (CISS) effect in chiral molecules and engineered nanomaterials. The CISS effect underpins the fact that charge transport through nanoscopic chiral structures favors a particular electronic spin orientation, resulting in large room-temperature spin polarizations. Observations of the CISS effect suggest opportunities for spin control and for the design and fabrication of room-temperature quantum devices from the bottom up, with atomic-scale precision. Any technology that relies on optimal charge transport, including quantum devices for logic, sensing, and storage, may benefit from chiral quantum properties. These properties can be theoretically and experimentally investigated from a quantum information perspective, which is presently lacking. There are uncharted implications for the quantum sciences once chiral couplings can be engineered to control the storage, transduction, and manipulation of quantum information. This forward-looking perspective provides a survey of the experimental and theoretical fundamentals of chiral-influenced quantum effects, and presents a vision for their future roles in enabling room-temperature quantum technologies.

cond-mat.mes-hall↗

arXiv2021

The Dynamical Ensemble of the Posner Molecule is not Symmetric

The Posner molecule, $\text{Ca}_9(\text{PO}_4)_6$, has long been recognized to have biochemical relevance in various physiological processes. It has found recent attention for its possible role as a biological quantum information processor, whereby the molecule purportedly maintains long-lived nuclear spin coherences among its ${^{31}\text{P}}$ nuclei (presumed to be symmetrically arranged), allowing it to function as a room temperature qubit. The structure of the molecule has been of much dispute in the literature, although the $\text{S}_6$ point group symmetry has often been assumed and exploited in calculations. Using a variety of simulation techniques (including ab initio molecular dynamics and structural relaxation), rigorous data analysis tools and by exploring thousands of individual configurations, we establish that the molecule predominantly assumes low symmetry structures ($\text{C}_\text{s}$ and $\text{C}_\text{i}$) at room temperature, as opposed to the higher symmetry configurations explored previously. Our findings have important implications on the viability of this molecule as a qubit.

quant-ph↗

arXiv2021

EaZy Learning: An Adaptive Variant of Ensemble Learning for Fingerprint Liveness Detection

In the field of biometrics, fingerprint recognition systems are vulnerable to presentation attacks made by artificially generated spoof fingerprints. Therefore, it is essential to perform liveness detection of a fingerprint before authenticating it. Fingerprint liveness detection mechanisms perform well under the within-dataset environment but fail miserably under cross-sensor (when tested on a fingerprint acquired by a new sensor) and cross-dataset (when trained on one dataset and tested on another) settings. To enhance the generalization abilities, robustness and the interoperability of the fingerprint spoof detectors, the learning models need to be adaptive towards the data. We propose a generic model, EaZy learning which can be considered as an adaptive midway between eager and lazy learning. We show the usefulness of this adaptivity under cross-sensor and cross-dataset environments. EaZy learning examines the properties intrinsic to the dataset while generating a pool of hypotheses. EaZy learning is similar to ensemble learning as it generates an ensemble of base classifiers and integrates them to make a prediction. Still, it differs in the way it generates the base classifiers. EaZy learning develops an ensemble of entirely disjoint base classifiers which has a beneficial influence on the diversity of the underlying ensemble. Also, it integrates the predictions made by these base classifiers based on their performance on the validation data. Experiments conducted on the standard high dimensional datasets LivDet 2011, LivDet 2013 and LivDet 2015 prove the efficacy of the model under cross-dataset and cross-sensor environments.

cs.CV↗

arXiv2020

AILearn: An Adaptive Incremental Learning Model for Spoof Fingerprint Detection

Incremental learning enables the learner to accommodate new knowledge without retraining the existing model. It is a challenging task which requires learning from new data as well as preserving the knowledge extracted from the previously accessed data. This challenge is known as the stability-plasticity dilemma. We propose AILearn, a generic model for incremental learning which overcomes the stability-plasticity dilemma by carefully integrating the ensemble of base classifiers trained on new data with the current ensemble without retraining the model from scratch using entire data. We demonstrate the efficacy of the proposed AILearn model on spoof fingerprint detection application. One of the significant challenges associated with spoof fingerprint detection is the performance drop on spoofs generated using new fabrication materials. AILearn is an adaptive incremental learning model which adapts to the features of the ``live'' and ``spoof'' fingerprint images and efficiently recognizes the new spoof fingerprints as well as the known spoof fingerprints when the new data is available. To the best of our knowledge, AILearn is the first attempt in incremental learning algorithms that adapts to the properties of data for generating a diverse ensemble of base classifiers. From the experiments conducted on standard high-dimensional datasets LivDet 2011, LivDet 2013 and LivDet 2015, we show that the performance gain on new fake materials is significantly high. On an average, we achieve $49.57\%$ improvement in accuracy between the consecutive learning phases.

cs.LG↗

arXiv2019

Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks

Object detection-the computer vision task dealing with detecting instances of objects of a certain class (e.g., 'car', 'plane', etc.) in images-attracted a lot of attention from the community during the last 5 years. This strong interest can be explained not only by the importance this task has for many applications but also by the phenomenal advances in this area since the arrival of deep convolutional neural networks (DCNN). This article reviews the recent literature on object detection with deep CNN, in a comprehensive way, and provides an in-depth view of these recent advances. The survey covers not only the typical architectures (SSD, YOLO, Faster-RCNN) but also discusses the challenges currently met by the community and goes on to show how the problem of object detection can be extended. This survey also reviews the public datasets and associated state-of-the-art algorithms.

cs.CV↗

arXiv2019

EILearn: Learning Incrementally Using Previous Knowledge Obtained From an Ensemble of Classifiers

We propose an algorithm for incremental learning of classifiers. The proposed method enables an ensemble of classifiers to learn incrementally by accommodating new training data. We use an effective mechanism to overcome the stability-plasticity dilemma. In incremental learning, the general convention is to use only the knowledge acquired in the previous phase but not the previously seen data. We follow this convention by retaining the previously acquired knowledge which is relevant and using it along with the current data. The performance of each classifier is monitored to eliminate the poorly performing classifiers in the subsequent phases. Experimental results show that the proposed approach outperforms the existing incremental learning approaches.

cs.LG↗

arXiv2019

Structuring an unordered text document

Segmenting an unordered text document into different sections is a very useful task in many text processing applications like multiple document summarization, question answering, etc. This paper proposes structuring of an unordered text document based on the keywords in the document. We test our approach on Wikipedia documents using both statistical and predictive methods such as the TextRank algorithm and Google's USE (Universal Sentence Encoder). From our experimental results, we show that the proposed model can effectively structure an unordered document into sections.

cs.IR↗