arXiv subjects

Jisu Kim

Publications and source records attributed to Jisu Kim.

At least 37 records · Page 2Linked to original sources

arXiv2025

PINT: Physics-Informed Neural Time Series Models with Applications to Long-term Inference on WeatherBench 2m-Temperature Data

This paper introduces PINT (Physics-Informed Neural Time Series Models), a framework that integrates physical constraints into neural time series models to improve their ability to capture complex dynamics. We apply PINT to the ERA5 WeatherBench dataset, focusing on long-term forecasting of 2m-temperature data. PINT incorporates the Simple Harmonic Oscillator Equation as a physics-informed prior, embedding its periodic dynamics into RNN, LSTM, and GRU architectures. This equation's analytical solutions (sine and cosine functions) facilitate rigorous evaluation of the benefits of incorporating physics-informed constraints. By benchmarking against a linear regression baseline derived from its exact solutions, we quantify the impact of embedding physical principles in data-driven models. Unlike traditional time series models that rely on future observations, PINT is designed for practical forecasting. Using only the first 90 days of observed data, it iteratively predicts the next two years, addressing challenges posed by limited real-time updates. Experiments on the WeatherBench dataset demonstrate PINT's ability to generalize, capture periodic trends, and align with physical principles. This study highlights the potential of physics-informed neural models in bridging machine learning and interpretable climate applications. Our models and datasets are publicly available on GitHub: https://github.com/KV-Park.

cs.LG↗

arXiv2025

An efficient forgetting-aware fine-tuning framework for pretrained universal machine-learning interatomic potentials

Pretrained universal machine-learning interatomic potentials (MLIPs) have revolutionized computational materials science by enabling rapid atomistic simulations as efficient alternatives to ab initio methods. Fine-tuning pretrained MLIPs offers a practical approach to improving accuracy for materials and properties where predictive performance is insufficient. However, this approach often induces catastrophic forgetting, undermining the generalizability that is a key advantage of pretrained MLIPs. Herein, we propose reEWC, an advanced fine-tuning strategy that integrates Experience Replay and Elastic Weight Consolidation (EWC) to effectively balance forgetting prevention with fine-tuning efficiency. Using Li$_6$PS$_5$Cl (LPSC), a sulfide-based Li solid-state electrolyte, as a fine-tuning target, we show that reEWC significantly improves the accuracy of a pretrained MLIP, resolving well-known issues of potential energy surface softening and overestimated Li diffusivities. Moreover, reEWC preserves the generalizability of the pretrained MLIP and enables knowledge transfer to chemically distinct systems, including other sulfide, oxide, nitride, and halide electrolytes. Compared to Experience Replay and EWC used individually, reEWC delivers clear synergistic benefits, mitigating their respective limitations while maintaining computational efficiency. These results establish reEWC as a robust and effective solution for continual learning in MLIPs, enabling universal models that can advance materials research through large-scale, high-throughput simulations across diverse chemistries.

cond-mat.mtrl-sci↗

arXiv2025

Using Cross-Domain Detection Loss to Infer Multi-Scale Information for Improved Tiny Head Tracking

Head detection and tracking are essential for downstream tasks, but current methods often require large computational budgets, which increase latencies and ties up resources (e.g., processors, memory, and bandwidth). To address this, we propose a framework to enhance tiny head detection and tracking by optimizing the balance between performance and efficiency. Our framework integrates (1) a cross-domain detection loss, (2) a multi-scale module, and (3) a small receptive field detection mechanism. These innovations enhance detection by bridging the gap between large and small detectors, capturing high-frequency details at multiple scales during training, and using filters with small receptive fields to detect tiny heads. Evaluations on the CroHD and CrowdHuman datasets show improved Multiple Object Tracking Accuracy (MOTA) and mean Average Precision (mAP), demonstrating the effectiveness of our approach in crowded scenes.

cs.CV↗

arXiv2024

Causal effects based on distributional distances

Comparing counterfactual distributions can provide more nuanced and valuable measures for causal effects, going beyond typical summary statistics such as averages. In this work, we consider characterizing causal effects via distributional distances, focusing on two kinds of target parameters. The first is the counterfactual outcome density. We propose a doubly robust-style estimator for the counterfactual density and study its rates of convergence and limiting distributions. We analyze asymptotic upper bounds on the $L_q$ and the integrated $L_q$ risks of the proposed estimator, and propose a bootstrap-based confidence band. The second is a novel distributional causal effect defined by the $L_1$ distance between different counterfactual distributions. We study three approaches for estimating the proposed distributional effect: smoothing the counterfactual density, smoothing the $L_1$ distance, and imposing a margin condition. For each approach, we analyze asymptotic properties and error bounds of the proposed estimator, and discuss potential advantages and disadvantages. We go on to present a bootstrap approach for obtaining confidence intervals, and propose a test of no distributional effect. We conclude with a numerical illustration and a real-world example.

stat.ML↗

arXiv2024

Hierarchical and Density-based Causal Clustering

Understanding treatment effect heterogeneity is vital for scientific and policy research. However, identifying and evaluating heterogeneous treatment effects pose significant challenges due to the typically unknown subgroup structure. Recently, a novel approach, causal k-means clustering, has emerged to assess heterogeneity of treatment effect by applying the k-means algorithm to unknown counterfactual regression functions. In this paper, we expand upon this framework by integrating hierarchical and density-based clustering algorithms. We propose plug-in estimators that are simple and readily implementable using off-the-shelf algorithms. Unlike k-means clustering, which requires the margin condition, our proposed estimators do not rely on strong structural assumptions on the outcome process. We go on to study their rate of convergence, and show that under the minimal regularity conditions, the additional cost of causal clustering is essentially the estimation error of the outcome regression functions. Our findings significantly extend the capabilities of the causal clustering framework, thereby contributing to the progression of methodologies for identifying homogeneous subgroups in treatment response, consequently facilitating more nuanced and targeted interventions. The proposed methods also open up new avenues for clustering with generic pseudo-outcomes. We explore finite sample properties via simulation, and illustrate the proposed methods in voting and employment projection datasets.

stat.ME↗

arXiv2024

Data-efficient multi-fidelity training for high-fidelity machine learning interatomic potentials

Machine learning interatomic potentials (MLIPs) are used to estimate potential energy surfaces (PES) from ab initio calculations, providing near quantum-level accuracy with reduced computational costs. However, the high cost of assembling high-fidelity databases hampers the application of MLIPs to systems that require high chemical accuracy. Utilizing an equivariant graph neural network, we present an MLIP framework that trains on multi-fidelity databases simultaneously. This approach enables the accurate learning of high-fidelity PES with minimal high-fidelity data. We test this framework on the Li$_6$PS$_5$Cl and In$_x$Ga$_{1-x}$N systems. The computational results indicate that geometric and compositional spaces not covered by the high-fidelity meta-gradient generalized approximation (meta-GGA) database can be effectively inferred from low-fidelity GGA data, thus enhancing accuracy and molecular dynamics stability. We also develop a general-purpose MLIP that utilizes both GGA and meta-GGA data from the Materials Project, significantly enhancing MLIP performance for high-accuracy tasks such as predicting energies above hull for crystals in general. Furthermore, we demonstrate that the present multi-fidelity learning is more effective than transfer learning or $Δ$-learning an d that it can also be applied to learn higher-fidelity up to the coupled-cluster level. We believe this methodology holds promise for creating highly accurate bespoke or universal MLIPs by effectively expanding the high-fidelity dataset.

cond-mat.mtrl-sci↗

arXiv2024

Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning

The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that begins with simpler tasks and progresses to more complex ones, using criteria such as prompt length, attention scores, and loss values to structure the training data. Experiments with Mistral-7B (Jiang et al., 2023) and Gemma-7B (Team et al., 2024) models demonstrate that curriculum learning slightly improves performance compared to traditional random data shuffling. Notably, we observed that sorting data based on our proposed attention criteria generally led to better performance. This approach offers a sustainable method to enhance LLM performance without increasing model size or dataset volume, addressing scalability challenges in LLM training.

cs.CL↗

arXiv2024

Control Token with Dense Passage Retrieval

This study addresses the hallucination problem in large language models (LLMs). We adopted Retrieval-Augmented Generation(RAG) (Lewis et al., 2020), a technique that involves embedding relevant information in the prompt to obtain accurate answers. However, RAG also faced inherent issues in retrieving correct information. To address this, we employed the Dense Passage Retrieval(DPR) (Karpukhin et al., 2020) model for fetching domain-specific documents related to user queries. Despite this, the DPR model still lacked accuracy in document retrieval. We enhanced the DPR model by incorporating control tokens, achieving significantly superior performance over the standard DPR model, with a 13% improvement in Top-1 accuracy and a 4% improvement in Top-20 accuracy.

cs.CL↗

arXiv2024

One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations

As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. To this end, we investigate how users perceive the AI model and comprehend the generated information when they receive multiple, potentially inconsistent, outputs. Through a preliminary study, we identified five types of output inconsistencies. Based on these categories, we conducted a study (N=252) in which participants were given one or more LLM-generated passages to an information-seeking question. We found that inconsistency within multiple LLM-generated outputs lowered the participants' perceived AI capacity, while also increasing their comprehension of the given information. Specifically, we observed that this positive effect of inconsistencies was most significant for participants who read two passages, compared to those who read three. Based on these findings, we present design implications that, instead of regarding LLM output inconsistencies as a drawback, we can reveal the potential inconsistencies to transparently indicate the limitations of these models and promote critical LLM usage.

cs.HC↗

arXiv2024

Semi-Supervised Domain Adaptation for Wildfire Detection

Recently, both the frequency and intensity of wildfires have increased worldwide, primarily due to climate change. In this paper, we propose a novel protocol for wildfire detection, leveraging semi-supervised Domain Adaptation for object detection, accompanied by a corresponding dataset designed for use by both academics and industries. Our dataset encompasses 30 times more diverse labeled scenes for the current largest benchmark wildfire dataset, HPWREN, and introduces a new labeling policy for wildfire detection. Inspired by CoordConv, we propose a robust baseline, Location-Aware Object Detection for Semi-Supervised Domain Adaptation (LADA), utilizing a teacher-student based framework capable of extracting translational variance features characteristic of wildfires. With only using 1% target domain labeled data, our framework significantly outperforms our source-only baseline by a notable margin of 3.8% in mean Average Precision on the HPWREN wildfire dataset. Our dataset is available at https://github.com/BloomBerry/LADA.

cs.CV↗

arXiv2024

The Hall of Singularity: VR Experience of Prophecy by AI

"The Hall of Singularity" is an immersive art that creates personalized experiences of receiving prophecies from an AI deity through an integration of Artificial Intelligence (AI) and Virtual Reality (VR). As a metaphor for the mythologizing of AI in our society, "The Hall of Singularity" offers an immersive quasi-religious experience where individuals can encounter an AI that has the power to make prophecies. This journey enables users to experience and imagine a world with an omnipotent AI deity.

cs.HC↗

arXiv2024

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models

We propose a robust and reliable evaluation metric for generative models by introducing topological and statistical treatments for rigorous support estimation. Existing metrics, such as Inception Score (IS), Frechet Inception Distance (FID), and the variants of Precision and Recall (P&R), heavily rely on supports that are estimated from sample features. However, the reliability of their estimation has not been seriously discussed (and overlooked) even though the quality of the evaluation entirely depends on it. In this paper, we propose Topological Precision and Recall (TopP&R, pronounced 'topper'), which provides a systematic approach to estimating supports, retaining only topologically and statistically important features with a certain level of confidence. This not only makes TopP&R strong for noisy features, but also provides statistical consistency. Our theoretical and experimental results show that TopP&R is robust to outliers and non-independent and identically distributed (Non-IID) perturbations, while accurately capturing the true trend of change in samples. To the best of our knowledge, this is the first evaluation metric focused on the robust estimation of the support and provides its statistical consistency under noise.

cs.LG↗

arXiv2023

Dynamically generated axial-vector meson resonance in the chiral symmetry restored vacuum

We study the modification of the properties of the axial-vector meson, dynamically generated through the unitarization procedure, in the vacuum where the chiral symmetry is restored. This is accomplished by scaling the pion decay constant as the chiral order parameter while keeping the other input parameters fixed. We find that the mass and width of the axial-vector meson reduce to those of the vector meson, as anticipated by the Weinberg sum rules. The findings are consistent with the results of a recent QCD sum rule calculation, wherein the chiral order parameter is expressed through chiral symmetry-breaking four-quark operators, leading to the mass-squared difference scaling in proportion to variations in the chiral order parameter. We calculate the scaling behavior for the mass differences obtained from the unitarization method using both the physical and massless pion masses.

hep-ph↗

arXiv2023

Topological Learning for Motion Data via Mixed Coordinates

Topology can extract the structural information in a dataset efficiently. In this paper, we attempt to incorporate topological information into a multiple output Gaussian process model for transfer learning purposes. To achieve this goal, we extend the framework of circular coordinates into a novel framework of mixed valued coordinates to take linear trends in the time series into consideration. One of the major challenges to learn from multiple time series effectively via a multiple output Gaussian process model is constructing a functional kernel. We propose to use topologically induced clustering to construct a cluster based kernel in a multiple output Gaussian process model. This kernel not only incorporates the topological structural information, but also allows us to put forward a unified framework using topological information in time and motion series.

cs.LG↗

arXiv2023

On the estimation of persistence intensity functions and linear representations of persistence diagrams

The prevailing statistical approach to analyzing persistence diagrams is concerned with filtering out topological noise. In this paper, we adopt a different viewpoint and aim at estimating the actual distribution of a random persistence diagram, which captures both topological signal and noise. To that effect, Chazel and Divol (2019) proved that, under general conditions, the expected value of a random persistence diagram is a measure admitting a Lebesgue density, called the persistence intensity function. In this paper, we are concerned with estimating the persistence intensity function and a novel, normalized version of it -- called the persistence density function. We present a class of kernel-based estimators based on an i.i.d. sample of persistence diagrams and derive estimation rates in the supremum norm. As a direct corollary, we obtain uniform consistency rates for estimating linear representations of persistence diagrams, including Betti numbers and persistence surfaces. Interestingly, the persistence density function delivers stronger statistical guarantees.

math.ST↗

arXiv2022

The Information Ecosystem of Conspiracy Theory: Examining the QAnon Narrative on Facebook

There has been concern about the proliferation of the "QAnon" conspiracy theory on Facebook, but little is known about how its misleading narrative propagated on the world's largest social media platform. Thus, the present research analyzed content generated by 2,813 Facebook pages and groups that contributed to promoting the conspiracy narrative between 2017 and 2020. The result demonstrated that activities of QAnon pages and groups started a significant surge months before the 2020 U.S. Presidential Election. We found that these pages and groups increasingly relied on internal sources, i.e., Facebook accounts or their content on the platform, while their dependence on external information sources decreased continuously since 2017. It was also found that QAnon posts based on the Facebook internal sources attracted significantly more shares and comments compared with other QAnon posts. These findings suggest that QAnon pages and groups increasingly isolated themselves from sources outside Facebook while having more internal interactions within the platform, and the endogenous creation and circulation of disinformation might play a significant role in boosting the influence of the misleading narrative within Facebook. The findings imply that the efforts to tackle down disinformation on social media should target not only the cross-platform infiltration of falsehood but also the intra-platform production and propagation of disinformation.

cs.SI↗

arXiv2022

Image-based Early Detection System for Wildfires

Wildfires are a disastrous phenomenon which cause damage to land, loss of property, air pollution, and even loss of human life. Due to the warmer and drier conditions created by climate change, more severe and uncontrollable wildfires are expected to occur in the coming years. This could lead to a global wildfire crisis and have dire consequences on our planet. Hence, it has become imperative to use technology to help prevent the spread of wildfires. One way to prevent the spread of wildfires before they become too large is to perform early detection i.e, detecting the smoke before the actual fire starts. In this paper, we present our Wildfire Detection and Alert System which use machine learning to detect wildfire smoke with a high degree of accuracy and can send immediate alerts to users. Our technology is currently being used in the USA to monitor data coming in from hundreds of cameras daily. We show that our system has a high true detection rate and a low false detection rate. Our performance evaluation study also shows that on an average our system detects wildfire smoke faster than an actual person.

cs.CV↗

arXiv2022

$ϕ$ meson properties in nuclear matter from QCD sum rules with chirally separated four-quark condensates

The modification of the $ϕ$ meson spectrum in nuclear matter is studied in an updated QCD sum rule analysis, taking into account recent improvements in properly treating the chiral invariant and breaking components of four-quark condensates. Allowing both mass and decay width to change at finite density, the QCD sum rule analysis determines certain combinations of changes for these parameters that satisfy the sum rules equally well. A comprehensive error analysis, including uncertainties related to the behavior of various condensates at linear order in density, the employed renormalization scale and perturbative corrections of the Wilson coefficients, is used to compute the allowed ranges of these parameter combinations. We find that the $ϕ$ meson mass shift in nuclear matter is especially sensitive to the strange sigma term $σ_{sN}$, which determines the decrease of the strange quark condensate in nuclear matter. Specifically, we obtain a linear relation between the width $Γ_ϕ$ and mass shift $Δm_ϕ$ given as $ Γ_ϕ = aΔm_ϕ + bσ_{sN}+c$ with $a = (3.947^{+0.139}_{-0.130})$, $b = (0.936^{+0.180}_{-0.177} )$ and $c = -(7.707^{+4.791}_{-5.679}) \mathrm{MeV}$.

hep-ph↗