arXiv subjects

Jihoon Park

Publications and source records attributed to Jihoon Park.

At least 19 recordsLinked to original sources

arXiv2026

Hierarchical geometry and right-angled Artin groups in graph braid groups

For the unordered discrete configuration space $\mathrm{UD}_n(\mathsf{\Gamma})$ of $n$ particles on a connected finite graph $\mathsf{\Gamma}$, we construct an explicit factor system on its universal cover. Its factors are encoded by legal pairs, namely subgraphs equipped with particle distributions. The nesting, orthogonality, and product regions in the resulting hierarchically hyperbolic group (HHG) structure admit explicit descriptions in terms of configuration-space geometry, and we show that this structure satisfies the additional properties needed for constructing and obstructing subgroups isomorphic to right-angled Artin groups (RAAGs). Using sufficiently subdivided models, we apply this hierarchy to graph braid groups. We give a finite combinatorial formula for the maximal rank of a free abelian subgroup and show that every RAAG occurs as an undistorted subgroup of some graph braid group. For graph $2$-braid groups, we obtain stronger restrictions: every RAAG subgroup has bipartite defining graph, and the embedding problem is characterized by an induced-subgraph condition in the expanded core graph of the hierarchy. For the RAAG defined by the four-vertex path, this condition is equivalent to a finite graphical criterion on the underlying graph.

math.GR↗

arXiv2026

Significant modulation of acoustoelectric current associated with charge density wave transitions

We studied acoustoelectric (AE) currents in materials that undergo charge density wave (CDW) transitions, induced by a surface acoustic wave (SAW) on a piezoelectric substrate. The polarity and magnitude of the AE current in NbSe$_3$ and 2H-TaSe$_2$ were modulated due to their CDW transitions. We also found that the sign of the AE current depends on the SAW propagation direction with respect to the crystalline axis of the substrate.A phenomenological model assuming strain-modified conductivity can qualitatively account for the significant modulation of the AE current associated with the CDW transition, as well as the SAW propagation orientation dependence. The present results offer a powerful probe for exploring SAW-electron interactions in van der Waals materials, thereby highlighting their potential for advancing the emerging field of straintronics.

cond-mat.mes-hall↗

arXiv2026

From algebraic orthogonality to RAAG embedding obstructions in hierarchically hyperbolic groups

We introduce the $\textit{expanded core graph}$, which records minimal unbounded domains and their axial directions, for two classes of hierarchically hyperbolic group structures modeled on compact special groups and mapping class groups. Our main structural result shows that every embedding of a right-angled Artin group, after replacing its standard generators by positive powers, factors through an intermediate RAAG generated by suitably supported axial elements; for the class modeled on compact special groups, this intermediate RAAG is quasi-isometrically embedded. We show that its extension graph embeds into the expanded core graph. This yields a Kim--Koberda-type obstruction to RAAG embeddings and a complete embedding criterion when the rank is at most two. For the standard HHG structure on a mapping class group, the expanded core graph is the disjointness graph of essential curves, while for natural rich-family structures on a RAAG it recovers the extension graph. We also establish permanence results under finite direct products and the standard relatively hyperbolic construction.

math.GR↗

arXiv2025

Observation of Shapiro Steps in the Charge Density Wave State Induced by Strain on a Piezoelectric Substrate

Recent development in nanotechnology has enabled us to investigate the dynamic properties of van der Waals materials on a piezoelectric substrate. Here we report on the dynamics of charge density wave (CDW) in NbSe$_{3}$ nanowires induced by surface acoustic waves (SAWs). Clear peaks in the differential resistance were observed at the resonant frequency of the SAW device. These peaks known as Shapiro steps are typically observed by applying an rf current to NbSe$_{3}$ nanowires. We found that the Shapiro steps induced by SAWs show several distinct features from the ones induced by an rf current. Our detailed study revealed that a strain induced by SAWs plays a significant role in the Shapiro steps. The result clearly demonstrates the importance of the strain in CDW materials and paves the way for strain-induced device applications.

cond-mat.mes-hall↗

arXiv2025

Embeddability of right-angled Artin groups into hierarchically hyperbolic groups

For a hierarchically hyperbolic group, we give sufficient conditions ensuring that suitable powers of a finite collection of elements generate a right-angled Artin subgroup; under an additional condition, this subgroup is undistorted. We verify these hypotheses in two natural situations: one modeled on mapping class groups, using structural assumptions on the ambient HHG, and one modeled on RAAGs, requiring the chosen elements to be rigidly fully supported. Our results recover known embedding theorems for mapping class groups and extend the non-annular undistortion theorem of Clay--Leininger--Mangahas, while also recovering the Kim--Koberda extension graph theorem for RAAGs.

math.GR↗

arXiv2025

Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding

To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with powerful cloud-based LLMs. Recent studies on HLM have primarily focused on improving accuracy and latency, while often overlooking communication and energy efficiency. We propose a token-level filtering mechanism for an energy-efficient importance- and uncertainty-aware HLM inference that leverages both epistemic uncertainty and attention-based importance. Our method opportunistically uploads only informative tokens, reducing LLM usage and communication costs. Experiments with TinyLlama-1.1B and LLaMA-2-7B demonstrate that our method achieves up to 87.5% BERT Score and token throughput of 0.37 tokens/sec while saving the energy consumption by 40.7% compared to standard HLM. Furthermore, compared to our previous U-HLM baseline, our method improves BERTScore from 85.8% to 87.0%, energy savings from 31.6% to 43.6%, and throughput from 0.36 to 0.40. This approach enables an energy-efficient and accurate deployment of LLMs in bandwidth-constrained edge environments.

cs.LG↗

arXiv2025

COMPASS: A Compiler Framework for Resource-Constrained Crossbar-Array Based In-Memory Deep Learning Accelerators

Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are currently limited to the case where all weights are assumed to be on-chip. This limitation becomes apparent with the significantly increasing network sizes compared to the in-memory footprint. Weight replacement schemes are essential to address this issue. We propose COMPASS, a compiler framework for resource-constrained crossbar-based processing-in-memory (PIM) deep neural network (DNN) accelerators. COMPASS is specially targeted for networks that exceed the capacity of PIM crossbar arrays, necessitating access to external memories. We propose an algorithm to determine the optimal partitioning that divides the layers so that each partition can be accelerated on chip. Our scheme takes into account the data dependence between layers, core utilization, and the number of write instructions to minimize latency, memory accesses, and improve energy efficiency. Simulation results demonstrate that COMPASS can accommodate much more networks using a minimal memory footprint, while improving throughput by 1.78X and providing 1.28X savings in energy-delay product (EDP) over baseline partitioning methods.

cs.AR↗

arXiv2024

DiffSLT: Enhancing Diversity in Sign Language Translation via Diffusion Model

Sign language translation (SLT) is challenging, as it involves converting sign language videos into natural language. Previous studies have prioritized accuracy over diversity. However, diversity is crucial for handling lexical and syntactic ambiguities in machine translation, suggesting it could similarly benefit SLT. In this work, we propose DiffSLT, a novel gloss-free SLT framework that leverages a diffusion model, enabling diverse translations while preserving sign language semantics. DiffSLT transforms random noise into the target latent representation, conditioned on the visual features of input video. To enhance visual conditioning, we design Guidance Fusion Module, which fully utilizes the multi-level spatiotemporal information of the visual features. We also introduce DiffSLT-P, a DiffSLT variant that conditions on pseudo-glosses and visual features, providing key textual guidance and reducing the modality gap. As a result, DiffSLT and DiffSLT-P significantly improve diversity over previous gloss-free SLT methods and achieve state-of-the-art performance on two SLT datasets, thereby markedly improving translation quality.

cs.CV↗

arXiv2024

Factor system for graphs and combinatorial HHS

We relaxe the constraint on the domains of combinatorial HHS machinery so combinatorial HHS machinery works for most cubical curve graphs. As an application we extend the factor system machinery of the CAT(0) cube complex to the quasi-median graphs.

math.GT↗

arXiv2024

Oscillations enhance time-series prediction in reservoir computing with feedback

Reservoir computing, a machine learning framework used for modeling the brain, can predict temporal data with little observations and minimal computational resources. However, it is difficult to accurately reproduce the long-term target time series because the reservoir system becomes unstable. This predictive capability is required for a wide variety of time-series processing, including predictions of motor timing and chaotic dynamical systems. This study proposes oscillation-driven reservoir computing (ODRC) with feedback, where oscillatory signals are fed into a reservoir network to stabilize the network activity and induce complex reservoir dynamics. The ODRC can reproduce long-term target time series more accurately than conventional reservoir computing methods in a motor timing and chaotic time-series prediction tasks. Furthermore, it generates a time series similar to the target in the unexperienced period, that is, it can learn the abstract generative rules from limited observations. Given these significant improvements made by the simple and computationally inexpensive implementation, the ODRC would serve as a practical model of various time series data. Moreover, we will discuss biological implications of the ODRC, considering it as a model of neural oscillations and their cerebellar processors.

cs.LG↗

arXiv2024

ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis

In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's dataset. Although various works with similar purposes have been actively studied, their performance has not yet reached that of trained multi-speaker models due to their fundamental limitations. To overcome previous limitations, we propose effective methods for feature learning and representing target speakers' speech characteristics by discretizing the features and conditioning them to a speech synthesis model. Our method obtained a significantly higher similarity mean opinion score (SMOS) in subjective similarity evaluation than seen speakers of a high-performance multi-speaker model, even with unseen speakers. The proposed method also outperforms a zero-shot method by significant margins. Furthermore, our method shows remarkable performance in generating new artificial speakers. In addition, we demonstrate that the encoded latent features are sufficiently informative to reconstruct an original speaker's speech completely. It implies that our method can be used as a general methodology to encode and reconstruct speakers' characteristics in various tasks.

cs.SD↗

arXiv2024

New Versions of Gradient Temporal Difference Learning

Sutton, Szepesvári and Maei introduced the first gradient temporal-difference (GTD) learning algorithms compatible with both linear function approximation and off-policy training. The goal of this paper is (a) to propose some variants of GTDs with extensive comparative analysis and (b) to establish new theoretical analysis frameworks for the GTDs. These variants are based on convex-concave saddle-point interpretations of GTDs, which effectively unify all the GTDs into a single framework, and provide simple stability analysis based on recent results on primal-dual gradient dynamics. Finally, numerical comparative analysis is given to evaluate these approaches.

cs.LG↗

arXiv2023

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has made great progress, there is room for improvement in terms of its intermittent unnaturalness, computational efficiency, and strong dependence on phoneme conversion. In this work, we introduce VITS2, a single-stage text-to-speech model that efficiently synthesizes a more natural speech by improving several aspects of the previous work. We propose improved structures and training mechanisms and present that the proposed methods are effective in improving naturalness, similarity of speech characteristics in a multi-speaker model, and efficiency of training and inference. Furthermore, we demonstrate that the strong dependence on phoneme conversion in previous works can be significantly reduced with our method, which allows a fully end-to-end single-stage approach.

cs.SD↗

arXiv2023

SplitAMC: Split Learning for Robust Automatic Modulation Classification

Automatic modulation classification (AMC) is a technology that identifies a modulation scheme without prior signal information and plays a vital role in various applications, including cognitive radio and link adaptation. With the development of deep learning (DL), DL-based AMC methods have emerged, while most of them focus on reducing computational complexity in a centralized structure. This centralized learning-based AMC (CentAMC) violates data privacy in the aspect of direct transmission of client-side raw data. Federated learning-based AMC (FedeAMC) can bypass this issue by exchanging model parameters, but causes large resultant latency and client-side computational load. Moreover, both CentAMC and FedeAMC are vulnerable to large-scale noise occured in the wireless channel between the client and the server. To this end, we develop a novel AMC method based on a split learning (SL) framework, coined SplitAMC, that can achieve high accuracy even in poor channel conditions, while guaranteeing data privacy and low latency. In SplitAMC, each client can benefit from data privacy leakage by exchanging smashed data and its gradient instead of raw data, and has robustness to noise with the help of high scale of smashed data. Numerical evaluations validate that SplitAMC outperforms CentAMC and FedeAMC in terms of accuracy for all SNRs as well as latency.

eess.SP↗

arXiv2021

Dirac-Source Diode with Sub-unity Ideality Factor

An increase in power consumption necessitates a low-power circuit technology to extend Moore's law. Low-power transistors, such as tunnel field-effect transistors (TFETs), negative-capacitance field-effect transistors (NC-FETs), and Dirac-source field-effect transistors (DS-FETs), have been realised to break the thermionic limit of the subthreshold swing (SS). However, a low-power diode rectifier, which breaks the thermionic limit of an ideality factor (n) of 1 at room temperature, has not been proposed yet. In this study, we have realised a DS Schottky diode, which exhibits a steep-slope characteristic curve, by utilising the linear density of states (DOSs) of graphene. For the developed DS Schottky diode, n<1 for more than two decades of drain current with a minimum value of 0.8, and the rectifying ratio is large (100000). The realisation of a DS Schottky diode paves the way for the development of low-power electronic circuits.

cond-mat.mes-hall↗

arXiv2021

Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution

Binarization of neural network models is considered as one of the promising methods to deploy deep neural network models on resource-constrained environments such as mobile devices. However, Binary Neural Networks (BNNs) tend to suffer from severe accuracy degradation compared to the full-precision counterpart model. Several techniques were proposed to improve the accuracy of BNNs. One of the approaches is to balance the distribution of binary activations so that the amount of information in the binary activations becomes maximum. Based on extensive analysis, in stark contrast to previous work, we argue that unbalanced activation distribution can actually improve the accuracy of BNNs. We also show that adjusting the threshold values of binary activation functions results in the unbalanced distribution of the binary activation, which increases the accuracy of BNN models. Experimental results show that the accuracy of previous BNN models (e.g. XNOR-Net and Bi-Real-Net) can be improved by simply shifting the threshold values of binary activation functions without requiring any other modification.

cs.LG↗

arXiv2020

Designing Artificial Two-Dimensional Landscapes via Room-Temperature Atomic-Layer Substitution

Manipulating materials with atomic-scale precision is essential for the development of next-generation material design toolbox. Tremendous efforts have been made to advance the compositional, structural, and spatial accuracy of material deposition and patterning. The family of 2D materials provides an ideal platform to realize atomic-level material architectures. The wide and rich physics of these materials have led to fabrication of heterostructures, superlattices, and twisted structures with breakthrough discoveries and applications. Here, we report a novel atomic-scale material design tool that selectively breaks and forms chemical bonds of 2D materials at room temperature, called atomic-layer substitution (ALS), through which we can substitute the top layer chalcogen atoms within the 3-atom-thick transition-metal dichalcogenides using arbitrary patterns. Flipping the layer via transfer allows us to perform the same procedure on the other side, yielding programmable in-plane multi-heterostructures with different out-of-plane crystal symmetry and electric polarization. First-principle calculations elucidate how the ALS process is overall exothermic in energy and only has a small reaction barrier, facilitating the reaction to occur at room temperature. Optical characterizations confirm the fidelity of this design approach, while TEM shows the direct evidence of Janus structure and suggests the atomic transition at the interface of designed heterostructure. Finally, transport and Kelvin probe measurements on MoXY (X,Y=S,Se; X and Y corresponding to the bottom and top layers) lateral multi-heterostructures reveal the surface potential and dipole orientation of each region, and the barrier height between them. Our approach for designing artificial 2D landscape down to a single layer of atoms can lead to unique electronic, photonic and mechanical properties previously not found in nature.

cond-mat.mtrl-sci↗

arXiv2018

Compensated Integrated Gradients to Reliably Interpret EEG Classification

Integrated gradients are widely employed to evaluate the contribution of input features in classification models because it satisfies the axioms for attribution of prediction. This method, however, requires an appropriate baseline for reliable determination of the contributions. We propose a compensated integrated gradients method that does not require a baseline. In fact, the method compensates the attributions calculated by integrated gradients at an arbitrary baseline using Shapley sampling. We prove that the method retrieves reliable attributions if the processes of input features in a classifier are mutually independent, and they are identical like shared weights in convolutional neural networks. Using three electroencephalogram datasets, we experimentally demonstrate that the attributions of the proposed method are more reliable than those of the original integrated gradients, and its computational complexity is much lower than that of Shapley sampling.

cs.LG↗