arXiv subjects

Jaeung Lee

Publications and source records attributed to Jaeung Lee.

6 recordsLinked to original sources

arXiv2026

Strain-tuned orbital-dependent electronic correlations in FeTe thin films

Iron chalcogenides exhibit rich phenomena which are governed by orbital-dependent electronic interactions and strong electronic correlation. In particular, many studies have explored orbital selectivity in FeTe through Se doping. Here, applying tensile strain to thin films allows us to precisely control the system without other impurities that may arise from chemical doping to investigate the emergent behaviors in FeTe. Using angle-resolved photoemission spectroscopy, we observe a spectral weight transfer between $d_{\rm xy}$ and $d_{\rm z^{2}}$ orbitals, evidence of an orbital-selective Mott phase (OSMP). Beyond OSMP, we reveal hitherto unobserved strain-induced effects, distinct from chemical doping. The evolution of $d_{\rm xz}$ orbital demonstrates how electron hopping mechanism plays an important role in defining the electronic properties of the system. Our findings highlight a direct correlation between epitaxial strain and the evolution of electronic structures in FeTe.

cond-mat.str-el↗

arXiv2026

Measuring the Depth of LLM Unlearning via Activation Patching

Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether target knowledge is truly erased remains challenging. Existing output-level metrics fail to detect when this knowledge remains recoverable from internal representations. Recent white-box studies reveal such residual knowledge but often rely on auxiliary training or dataset-specific adaptations, leaving no generalizable metric. We close this gap with the Unlearning Depth Score (UDS), a metric that quantifies the mechanistic depth of unlearning via activation patching. UDS first identifies layers that encode the target knowledge using a retain model baseline, then measures how much of it is erased in the unlearned model on a 0-1 scale. In a meta-evaluation across 20 metrics on 150 unlearned models spanning 8 methods, UDS achieves the highest faithfulness and robustness, confirming our causal approach as the most reliable for unlearning evaluation. Case studies further show that UDS uncovers residual knowledge obscured from observational metrics by representational shifts, with erasure depth varying across prompt types. We provide guidelines for integrating UDS into existing benchmarking frameworks and streamlining the evaluation pipeline. Code and data are available at https://github.com/gnueaj/unlearning-depth-score.

cs.CL↗

arXiv2026

Suppression or Deletion: A Restoration-Based Representation-Level Analysis of Machine Unlearning

As pretrained models are increasingly shared on the web, ensuring that models can forget or delete sensitive, copyrighted, or private information upon request has become crucial. Machine unlearning has been proposed to address this challenge. However, current evaluations for unlearning methods rely on output-based metrics, which cannot verify whether information is completely deleted or merely suppressed at the representation level, where suppression is insufficient for true unlearning. To address this gap, we propose a novel restoration-based analysis framework that uses Sparse Autoencoders to identify class-specific expert features in intermediate layers and applies inference-time steering to quantitatively distinguish between suppression and deletion. Applying our framework to 12 major unlearning methods in image classification tasks, we find that most methods achieve high restoration rates of unlearned information, indicating that they only suppress information at the decision-boundary level, while preserving semantic features in intermediate representations. Notably, even retraining from pretrained checkpoints shows high restoration, revealing that robust semantic features inherited from pretraining are not removed by retraining. These results demonstrate that representation-level retention poses significant risks overlooked by output-based metrics, highlighting the need for new unlearning evaluation criteria. We propose new evaluation guidelines that prioritize representation-level verification, especially for privacy-critical applications in the era of pre-trained models.

cs.CV↗

arXiv2026

Superconductivity in Isolated Single Copper Oxygen Plane

One of the central questions in cuprate superconductivity is if superconductivity can exist in an isolated single CuO$_2$ plane without any interlayer coupling. There have been numerous experimental efforts to answer this question, but it still has not been clearly resolved. Here we present a heterostructure system with an isolated half-unit-cell La$_{2-x}$Sr$_x$CuO$_4$ which has a single CuO$_2$ plane. Using in-situ angle-resolved photoemission spectroscopy, we measured the electronic and gap structures of a single CuO$_2$ plane. We observed a \textit{d}-wave-like gap which closes somewhat above the bulk T$_c$. Moreover, almost identical gap properties are seen for both single CuO$_2$ plane and bulk. These observations lead us to the conclusion that the d-wave superconductivity of cuprates also exists in a single CuO$_2$ plane. Our results demonstrate that cuprate superconductivity is essentially a two-dimensional phenomenon and provide a platform to study cuprate superconductivity in a purely two-dimensional system.

cond-mat.supr-con↗

arXiv2025

Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods

Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe that researchers in this rapidly emerging field face challenges in analyzing and understanding the behavior of different MU methods, especially in terms of three fundamental principles in MU: accuracy, efficiency, and privacy. Consequently, they often rely on aggregate metrics and ad-hoc evaluations, making it difficult to accurately assess the trade-offs between methods. To fill this gap, we introduce a visual analytics system, Unlearning Comparator, designed to facilitate the systematic evaluation of MU methods. Our system supports two important tasks in the evaluation process: model comparison and attack simulation. First, it allows the user to compare the behaviors of two models, such as a model generated by a certain method and a retrained baseline, at class-, instance-, and layer-levels to better understand the changes made after unlearning. Second, our system simulates membership inference attacks (MIAs) to evaluate the privacy of a method, where an attacker attempts to determine whether specific data samples were part of the original training set. We evaluate our system through a case study visually analyzing prominent MU methods and demonstrate that it helps the user not only understand model behaviors but also gain insights that can inform the improvement of MU methods. The source code is publicly available at https://github.com/gnueaj/Machine-Unlearning-Comparator.

cs.CR↗

arXiv2023

Centroid-aware feature recalibration for cancer grading in pathology images

Cancer grading is an essential task in pathology. The recent developments of artificial neural networks in computational pathology have shown that these methods hold great potential for improving the accuracy and quality of cancer diagnosis. However, the issues with the robustness and reliability of such methods have not been fully resolved yet. Herein, we propose a centroid-aware feature recalibration network that can conduct cancer grading in an accurate and robust manner. The proposed network maps an input pathology image into an embedding space and adjusts it by using centroids embedding vectors of different cancer grades via attention mechanism. Equipped with the recalibrated embedding vector, the proposed network classifiers the input pathology image into a pertinent class label, i.e., cancer grade. We evaluate the proposed network using colorectal cancer datasets that were collected under different environments. The experimental results confirm that the proposed network is able to conduct cancer grading in pathology images with high accuracy regardless of the environmental changes in the datasets.

cs.CV↗