arXiv subjects

Jaekwang Kim

Publications and source records attributed to Jaekwang Kim.

At least 19 recordsLinked to original sources

arXiv2026

PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation

Retrieval-Augmented Generation enhances Large Language Models by grounding responses in external knowledge, but multi-hop reasoning remains vulnerable to error propagation, where early retrieval failures confound subsequent steps. Standard outcome-based optimization only rewards the final answer, leaving intermediate retrieval and reasoning errors undetected. While existing process-based methods introduce step-level signals, they still score each step against the final answer, rewarding spurious successes where flawed retrieval coincidentally produces the correct answer. Step-level supervision in RAG requires evaluating both logical validity and evidential grounding at each step. We introduce PRO-STEP: we train a generative PRM that evaluates both dimensions, employ PRM-guided value tree search to construct preference pairs contrasting valid steps against flawed ones, and optimize the policy via step-level Direct Preference Optimization. Experiments on single and multi-hop QA datasets demonstrate that PRO-STEP achieves the best average EM and F1 across five benchmarks. Code, models, and training data are publicly available at https://github.com/keemminnke/PRO-Step.

cs.CL↗

arXiv2026

SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization

Pixel-aligned Gaussian splatting enables efficient and generalizable novel-view synthesis. However, high-resolution rendering faces a critical trade-off where increasing input resolution improves detail at the expense of quadratically rising network computational cost. Conversely, maintaining low-resolution inputs stabilizes this cost but results in insufficient Gaussian density and artifacts. To address this, we propose SubSplat, which introduces Sub-pixel Gaussian Reparameterizer(SPGR) to subdivide primary Gaussians into fine-grained primitives, restoring structural density directly from low-resolution features. We further enhance the reparameterization quality through feature aggregation, which effectively captures high-frequency details across multiple views. Experiments on RealEstate10K and ACID demonstrate that SubSplat achieves high-fidelity rendering with superior efficiency. Our results validate that the proposed framework successfully resolves the trade-off between reparameterization fidelity and network computational cost inherent in pixel-aligned Gaussian Splatting.

cs.CV↗

arXiv2026

Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots

Tracking multi-person 3D human meshes from in-the-wild videos is a highly challenging problem due to complex interactions, frequent occlusions, and severe truncation inherent in unconstrained environments. While recent approaches have improved robustness against these issues, they largely overlook the critical challenge prevalent in real-world footage: frequent shot changes. These abrupt transitions in camera viewpoints often cause existing methods to lose track of human identities and fail in reconstructing temporally coherent trajectories. Although several recent works have explored 3D human mesh tracking under shot changes, they are still limited to single-person scenarios, making them inadequate for real-world videos where multiple people interact and appear simultaneously. To address this limitation, we propose Multi-THuMBS (Multi-person Tracking of 3D Human Meshes Beyond Video Shots) that leverages a state-of-the-art 3D scene prior to reconstruct the two boundary frames in a single shared 3D space. Human meshes are then registered within the shared 3D space, maintaining per-person identity and motion consistency across shot changes. Extensive experiments demonstrate that our approach yields significant improvements in 3D human mesh recovery, camera pose estimation, and identity tracking, thereby ensuring high-fidelity motion reconstruction with consistent identity preservation across shots compared to previous state-of-the-art methods.

cs.CV↗

arXiv2025

Uncertainty quantification and parameter optimization of plasma etching process using heteroscedastic Gaussian process

This study presents a comprehensive framework for uncertainty quantification (UQ) and design optimization of plasma etching in semiconductor manufacturing. The framework is demonstrated using experimental measurements of etched depth collected at nine wafer locations under various plasma conditions. A heteroscedastic Gaussian process (hetGP) surrogate model is employed to capture the complex uncertainty structure in the data, enabling distinct quantification of (a) spatial variability across the wafer and (b) process-related uncertainty arising from variations in chamber pressure, gas flow rate, and RF power. Epistemic uncertainty due to sparse data is further quantified and incorporated into a reliability-based design optimization (RBDO) scheme. The proposed method identifies optimal process parameters that minimize spatial variability of etch depth while maintaining reliability under both aleatory and epistemic uncertainties. The results demonstrate that this framework effectively integrates data-driven surrogate modeling with robust optimization, enhancing predictive accuracy and process reliability. Moreover, the proposed approach is generalizable to other semiconductor processes, such as photolithography, where performance is highly sensitive to multifaceted uncertainties.

physics.pop-ph↗

arXiv2025

Graph-Based Learning of Free Surface Dynamics in Generalized Newtonian Fluids using Smoothed Particle Hydrodynamics

In this study, we propose a graph neural network (GNN) model for efficiently predicting the flow behavior of non-Newtonian fluids with free surface dynamics. The numerical analysis of non-Newtonian fluids presents significant challenges, as traditional algorithms designed for Newtonian fluids with constant viscosity often struggle to converge when applied to non-Newtonian cases, where rheological properties vary dynamically with flow conditions. Among these, power-law fluids exhibit viscosity that decreases exponentially as the shear rate increases, making numerical simulations particularly difficult. The complexity further escalates in free surface flow scenarios, where computational challenges intensify. In such cases, particle-based methods like smoothed particle hydrodynamics (SPH) provide advantages over traditional grid-based techniques, such as the finite element method (FEM). Building on this approach, we introduce a novel GNN-based numerical model to enhance the computational efficiency of non-Newtonian power-law fluid flow simulations. Our model is trained on SPH simulation data, learning the effects of particle accelerations in the presence of SPH interactions based on the fluid's power-law parameters. The GNN significantly accelerates computations while maintaining reliable accuracy in benchmark tests, including dam-break and droplet impact simulations. The results underscore the potential of GNN-based simulation frameworks for efficiently modeling non-Newtonian fluid behavior, paving the way for future advancements in data-driven fluid simulations.

physics.flu-dyn↗

arXiv2025

Numerical Modeling of n-Hexane Pyrolysis with an Optimized Kinetic Mechanism in a Hydrogen Plasma Reactor

The physicochemical mechanisms underlying the pyrolysis of n-hexane in a high temperature Ar-H2 environment were investigated for plasma pyrolysis process. An optimal chemical kinetics model was developed using the Reaction Mechanism Generator (RMG), an automated tool for constructing reaction mechanisms. This model was validated through 0-D analyses, where simulation result were compared with existing kinetic models (LLNL,JetSurf) and experimental data from conventional n-hexane pyrolysis. Subsequently, 1-D analysis were conducted to identify the optimal operational flow rate in plasma pyrolysis reactor, the results of which informed detailed three-dimensional (2-D) computational fluid dynamics (CFD) modeling of the plasma reactor. The CFD simulations reveal that fluid mixing dynamics play a dominant role in determining the extent of conversion and product selectivity, highlighting the limitations of lower-dimensional models in capturing essential transport phenomena. Notably, the simulations indicate a higher C2 monomer selectivity of approximately 50 % under plasma-based n-hexane pyrolysis, in contrast to the roughly 30 % selectivity achieved via conventional fossil-fuel-based methods. These findings underscore the potential advantages of plasma-driven pyrolysis and represent a critical step toward a comprehensive understanding of the complex thermochemical behavior governing plasma-assisted processes.

physics.plasm-ph↗

arXiv2025

In-situ and Non-contact Etch Depth Prediction in Plasma Etching via Machine Learning (ANN & BNN) and Digital Image Colorimetry

Precise monitoring of etch depth and the thickness of insulating materials, such as Silicon dioxide and silicon nitride, is critical to ensuring device performance and yield in semiconductor manufacturing. While conventional ex-situ analysis methods are accurate, they are constrained by time delays and contamination risks. To address these limitations, this study proposes a non-contact, in-situ etch depth prediction framework based on machine learning (ML) techniques. Two scenarios are explored. In the first scenario, an artificial neural network (ANN) is trained to predict average etch depth from process parameters, achieving a significantly lower mean squared error (MSE) compared to a linear baseline model. The approach is then extended to incorporate variability from repeated measurements using a Bayesian Neural Network (BNN) to capture both aleatoric and epistemic uncertainty. Coverage analysis confirms the BNN's capability to provide reliable uncertainty estimates. In the second scenario, we demonstrate the feasibility of using RGB data from digital image colorimetry (DIC) as input for etch depth prediction, achieving strong performance even in the absence of explicit process parameters. These results suggest that the integration of DIC and ML offers a viable, cost-effective alternative for real-time, in-situ, and non-invasive monitoring in plasma etching processes, contributing to enhanced process stability, and manufacturing efficiency.

cs.CV↗

arXiv2025

C$^3$: Capturing Consensus with Contrastive Learning in Group Recommendation

Group recommendation aims to recommend tailored items to groups of users, where the key challenge is modeling a consensus that reflects member preferences. Although several existing deep learning models have achieved performance improvements, they still fail to capture consensus in various aspects: (1) Capturing consensus in small-group (2~5 members) recommendation systems, which align more closely with real-world scenarios, remains a significant challenge; (2) Most existing models significantly enhance the overall group performance but struggle with balancing individual and group performance. To address these issues, we propose Capturing Consensus with Contrastive Learning in Group Recommendation (C$^3$), which focuses on exploring the consensus behind group decision-making. A Transformer encoder is used to learn both group and user representations, and contrastive learning mitigates overfitting for users with many interactions, yielding more robust group representations. Experiments on four public datasets demonstrate that C$^3$ significantly outperforms state-of-the-art baselines in both user and group recommendation tasks.

cs.IR↗

arXiv2025

Comparative Analysis of Granular Material Flow: Discrete Element Method and Smoothed Particle Hydrodynamics Approaches

We compare two widely used Lagrangian approaches for modeling granular materials: the Discrete Element Method (DEM) and Smoothed Particle Hydrodynamics (SPH). DEM models individual particle interactions, while SPH treats granular materials as a continuum using constitutive rheological models. In particular, we employ the Drucker Prager viscoplastic model for SPH. By examining key parameters unique to each method, such as the coefficient of restitution in DEM and the dilatancy angle in SPH, we assess their influence on two dimensional soil collapse predictions against experimental results. While DEM requires computationally expensive parameter calibration, SPH benefits from a continuum scale rheological model, allowing most parameters to be directly determined from laboratory measurements and requiring significantly fewer particles. However, despite its computational efficiency, viscoplastic SPH struggles to capture complex granular flow behaviors observed in DEM, particularly in rotating drum simulations. In contrast, DEM offers greater versatility, accommodating a broader range of flow patterns while maintaining a relatively simple model formulation. These findings provide valuable insights into the strengths and limitations of each method, aiding the selection of appropriate modeling techniques for granular flow simulations.

cond-mat.soft↗

arXiv2024

Debiasing Classifiers by Amplifying Bias with Latent Diffusion and Large Language Models

Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative Adversarial Networks (GANs) to mitigate biases. We introduce DiffuBias, a novel pipeline for text-to-image generation that enhances classifier robustness by generating bias-conflict samples, without requiring training during the generation phase. Utilizing pretrained diffusion and image captioning models, DiffuBias generates images that challenge the biases of classifiers, using the top-$K$ losses from a biased classifier ($f_B$) to create more representative data samples. This method not only debiases effectively but also boosts classifier generalization capabilities. To the best of our knowledge, DiffuBias is the first approach leveraging a stable diffusion model to generate bias-conflict samples in debiasing tasks. Our comprehensive experimental evaluations demonstrate that DiffuBias achieves state-of-the-art performance on benchmark datasets. We also conduct a comparative analysis of various generative models in terms of carbon emissions and energy consumption to highlight the significance of computational efficiency.

cs.CV↗

arXiv2024

DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection

Dataset bias is a significant challenge in machine learning, where specific attributes, such as texture or color of the images are unintentionally learned resulting in detrimental performance. To address this, previous efforts have focused on debiasing models either by developing novel debiasing algorithms or by generating synthetic data to mitigate the prevalent dataset biases. However, generative approaches to date have largely relied on using bias-specific samples from the dataset, which are typically too scarce. In this work, we propose, DiffInject, a straightforward yet powerful method to augment synthetic bias-conflict samples using a pretrained diffusion model. This approach significantly advances the use of diffusion models for debiasing purposes by manipulating the latent space. Our framework does not require any explicit knowledge of the bias types or labelling, making it a fully unsupervised setting for debiasing. Our methodology demonstrates substantial result in effectively reducing dataset bias.

cs.CV↗

arXiv2023

Segment-Based Wall Treatment Model for Heat Transfer Rate in Smoothed Particle Hydrodynamics

In this study, a smoothed particle hydrodynamics (SPH) model that applies a segment-based boundary treatment is used to simulate natural convection. In a natural convection simulated using an SPH model, the wall boundary treatment is a major issue because accurate heat transfer from boundaries should be calculated. The boundary particle method, which models the boundary by placing multiple layers of particles on and behind the wall boundary, is the most widely used boundary treatment method. Although this method can impose accurate boundary conditions, boundary modeling for complex shapes is challenging and requires excessive computational costs depending on the boundary shape. In this study, we utilize a segment-based boundary treatment method to model the wall boundary and apply this method to the energy conservation equation for the wall heat transfer model. The proposed method solves the problems arising from the use of boundary particles and simultaneously provides accurate heat transfer calculation results for the wall. In various numerical examples, the proposed method is verified through a comparison with available experimental results, SPH results using the boundary particle method, and finite volume method (FVM) results.

physics.flu-dyn↗

arXiv2023

Fast Marching based Rendezvous Path Planning for a Team of Heterogeneous Vehicle

This paper presents a formulation for deterministically calculating optimized paths for a multiagent system consisting of heterogeneous vehicles. The key idea is the calculation of the shortest time for each agent to reach every grid point from its known initial position. Such arrival time map is efficiently computed using the Fast Marching Method (FMM), a computational algorithm originally designed for solving boundary value problems of the Eikonal equation. By leveraging the FMM, we demonstrate that the minimal time rendezvous point and paths for all member vehicles can be uniquely determined with minimal computational overhead. The scalability and adaptability of the present method during online execution are investigated, followed by a comparison with a baseline method that highlights the effectiveness of the proposed approach. Then, the potential of the present method is showcased through a virtual rendezvous scenario involving the coordination of a ship, an underwater vehicle, an aerial vehicle, and a ground vehicle, all converging at the optimal location within the Tampa Bay area in minimal time. The results show that the developed framework can efficiently construct continuous paths of heterogeneous vehicles by accommodating operational constraints via an FMM algorithm

cs.MA↗

arXiv2023

Statistics of grain microstructure evolution under anisotropic grain boundary energies and mobilities using threshold-dynamics

This paper investigates the statistical behavior of two-dimensional grain microstructures during grain growth under anisotropic grain boundary characters. We employ the threshold-dynamics method, which allows for unparalleled computational speed, to simulate the full-field curvature motion of grain boundaries in a large polycrystal ensemble. Two sets of numerical experiments are performed to explore the effect of grain boundary anisotropy on the evolution of microstructure features. In the first experiment, we focus on abnormal grain growth and find that grain boundary anisotropy introduces a statistical preference for certain grain orientations. This leads to changes in the overall grain size distribution from the isotropic case. In the second experiment, we examine the texture development and growth of twin grain boundaries at different initial microstructures. We find that both phenomena are more pronounced when the initial microstructure has a dominant fraction of high-angle grain boundaries. Our results suggest effective grain boundary engineering strategies for improving material properties.

cond-mat.mtrl-sci↗

arXiv2023

Hierarchical Contrastive Learning with Multiple Augmentation for Sequential Recommendation

Sequential recommendation addresses the issue of preference drift by predicting the next item based on the user's previous behaviors. Recently, a promising approach using contrastive learning has emerged, demonstrating its effectiveness in recommending items under sparse user-item interactions. Significantly, the effectiveness of combinations of various augmentation methods has been demonstrated in different domains, particularly in computer vision. However, when it comes to augmentation within a contrastive learning framework in sequential recommendation, previous research has only focused on limited conditions and simple structures. Thus, it is still possible to extend existing approaches to boost the effects of augmentation methods by using progressed structures with the combinations of multiple augmentation methods. In this work, we propose a novel framework called Hierarchical Contrastive Learning with Multiple Augmentation for Sequential Recommendation(HCLRec) to overcome the aforementioned limitation. Our framework leverages existing augmentation methods hierarchically to improve performance. By combining augmentation methods continuously, we generate low-level and high-level view pairs. We employ a Transformers-based model to encode the input sequence effectively. Furthermore, we introduce additional blocks consisting of Transformers and position-wise feed-forward network(PFFN) layers to learn the invariance of the original sequences from hierarchically augmented views. We pass the input sequence to subsequent layers based on the number of increment levels applied to the views to handle various augmentation levels. Within each layer, we compute contrastive loss between pairs of views at the same level. Extensive experiments demonstrate that our proposed method outperforms state-of-the-art approaches and that HCLRec is robust even when faced with the problem of sparse interaction.

cs.IR↗

arXiv2021

A crystal symmetry-invariant Kobayashi--Warren--Carter grain boundary model and its implementation using a thresholding algorithm

One of the most important aims of grain boundary modeling is to predict the evolution of a large collection of grains in phenomena such as abnormal grain growth, coupled grain boundary motion, and recrystallization that occur under extreme thermomechanical loads. A unified framework to study the coevolution of grain boundaries with bulk plasticity has recently been developed by Admal et al. (2018), which is based on modeling grain boundaries as continuum dislocations governed by an energy based on the Kobayashi--Warren--Carter (KWC) model (Kobayashi et al., 1998, 2000). While the resulting unified model demonstrates coupled grain boundary motion and polygonization (seen in recrystallization), it is restricted to grain boundary energies of the Read--Shockley type, which applies only to small misorientation angles. In addition, the implementation of the unified model using finite elements inherits the computational challenges of the KWC model that originate from the singular diffusive nature of its governing equations. The main goal of this study is to generalize the KWC functional to grain boundary energies beyond the Read--Shockley-type that respect the bicrystallography of grain boundaries. The computational challenges of the KWC model are addressed by developing a thresholding method that relies on a primal dual algorithm and the fast marching method, resulting in an O(NlogN) algorithm, where N is the number of grid points. We validate the model by demonstrating the Herring angle relation, followed by a study of the grain microstructure evolution in a two-dimensional face-centered cubic copper polycrystal with crystal symmetry-invariant grain boundary energy data obtained from the lattice matching method of Runnels et al. (2016a,b).

cond-mat.mtrl-sci↗

arXiv2021

EPSR: Edge Profile Super resolution

In this paper, we propose Edge Profile Super Resolution(EPSR) method to preserve structure information and to restore texture. We make EPSR by stacking modified Fractal Residual Network(mFRN) structures hierarchically and repeatedly. mFRN is made up of lots of Residual Edge Profile Blocks(REPBs) consisting of three different modules such as Residual Efficient Channel Attention Block(RECAB) module, Edge Profile(EP) module, and Context Network(CN) module. RECAB produces more informative features with high frequency components. From the feature, EP module produce structure informed features by generating edge profile itself. Finally, CN module captures details by exploiting high frequency information such as texture and structure with proper sharpness. As repeating the procedure in mFRN structure, our EPSR could extract high-fidelity features and thus it prevents texture loss and preserves structure with appropriate sharpness. Experimental results present that our EPSR achieves competitive performance against state-of-the-art methods in PSNR and SSIM evaluation metrics as well as visual results.

eess.IV↗

arXiv2020

A Differentiable Ranking Metric Using Relaxed Sorting Operation for Top-K Recommender Systems

A recommender system generates personalized recommendations for a user by computing the preference score of items, sorting the items according to the score, and filtering top-K items with high scores. While sorting and ranking items are integral for this recommendation procedure, it is nontrivial to incorporate them in the process of end-to-end model training since sorting is nondifferentiable and hard to optimize with gradient descent. This incurs the inconsistency issue between existing learning objectives and ranking metrics of recommenders. In this work, we present DRM (differentiable ranking metric) that mitigates the inconsistency and improves recommendation performance by employing the differentiable relaxation of ranking metrics. Via experiments with several real-world datasets, we demonstrate that the joint learning of the DRM objective upon existing factor based recommenders significantly improves the quality of recommendations, in comparison with other state-of-the-art recommendation methods.

cs.IR↗