arXiv subjects

Jinho Lee

Publications and source records attributed to Jinho Lee.

At least 19 recordsLinked to original sources

arXiv2026

TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information

Existing GNN quantization methods suffer from considerable quantization overhead, which severely limits their practical usage in real-world scenarios. To this end, we present TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead. We propose dual-axis scale absorption, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix. On top of that, we introduce TopPIN, a proxy for nodes' local structure, and use it to group nodes with similar topology during quantization. Experimental results show that TopGQ reduces quantization time by an order of magnitude while preserving accuracy.

cs.LG↗

arXiv2026

SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision

In semiconductor manufacturing, defect analysis is essential, but manual inspection cannot scale. However, existing automated inspection methods remain insufficient for root-cause analysis and process optimization. To this end, we present SePArate, a weakly supervised wafer defect segmentation method. SePArate enables pixel-level separation of patterns by leveraging only image-level annotations. It consists of a three-phase training: encoder pretraining, knowledge transfer to learn spatial cues, and training on synthetic mixed-defect data for accurate segmentation. Experiments demonstrate that SePArate outperforms the baselines.

cs.CV↗

arXiv2026

STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation

The rapid expansion of low Earth orbit satellites such as Starlink is increasingly contaminating astronomical surveys. In practice, contaminated images are often identified through inspection. However, modern surveys generate terabytes of data each night, making manual screening infeasible and necessitating reliable automated methods for satellite trail removal. Unfortunately, existing general-domain line detection methods fail to generalize to astronomical images due to domain mismatch, which are mostly grayscale with sparse bright stars and have a low signal-to-noise ratio. Moreover, training new models from scratch is impractical due to the lack of large-scale annotated astronomical datasets. To address these challenges, we introduce STARLINC, the first ML-based framework for satellite trail removal without requiring tedious pixel-level annotation of astronomical images. STARLINC combines synthetic satellite trail generation for training, inter-frame differential maps from temporally adjacent exposures to highlight transient trails, and heatmaps to provide additional localization cues for pixel-level segmentation. Extensive experiments on real-world data demonstrate substantial improvements over baselines, establishing STARLINC as a scalable solution for next-generation astronomical surveys. Code is available at https://github.com/starioKim/STARLINC.

cs.CV↗

arXiv2026

CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents

Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers. Existing poisoning attacks often rely on query inclusion, inserting the target query into poisoned documents to improve retrieval; however, this creates lexical and embedding-space artifacts that make them easy to filter. We propose CamoDocs, a poisoning attack that avoids direct query inclusion by camouflaging adversarial documents among benign content. CamoDocs chunks synthesized benign and adversarial drafts, replaces selected tokens in benign chunks with dispersion tokens that spread poisoned-document embeddings, and applies coherence filtering to limit readability degradation. Across seven RAG defenses, three open-weight LLMs, and three benchmarks, CamoDocs achieves strong average ASR while avoiding query-overlap artifacts exploited by simple query detection. It also remains effective against proprietary models, achieving average ASRs of 61.80% on GPT-5.4-mini and 55.09% on Claude-Haiku-4.5. Finally, we show that erasure-heavy clustering defenses such as TrustRAG can reduce ASR, but only with substantial utility drops on retrieval-dependent benchmarks such as NeoQA. Code is available at https://github.com/jaewonalive/CamoDocs.

cs.CR↗

arXiv2026

AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL

Optimizing nonlinear preferences in multi-objective reinforcement learning (MORL) is essential for capturing complex trade-offs like risk aversion or fairness. However, such non-linearity has historically bifurcated nonlinear MORL objectives into two distinct paradigms: Scalarized Expected Return (SER) and Expected Scalarized Return (ESR). While SER requires global-level optimization and ESR requires non-Markovian policies, leading to fragmented optimization strategies, we bridge this divide through the Aggregation-Expectation-Transformation (AET) framework. By unifying both criteria through a tripartite decomposition of scalarization, AET provides a principled foundation for general nonlinear MORL. Building on this framework, we propose AETDICE, a tractable offline RL algorithm for AET objectives. By utilizing DICE-style density-ratio estimation in an augmented state space, AETDICE enables sample-based optimization from static datasets. Our framework resolves long-standing barriers and captures respective trade-offs induced by AET framework, which existing methods fail to address.

cs.LG↗

arXiv2026

7DT Insight: Variability in Young Stellar Objects

Photometric variability in young stellar objects (YSOs) provides critical insight into the mechanisms of mass accretion, disk evolution, and circumstellar extinction in early stellar evolution. We present an analysis of day-timescale optical variability in the Orion A central region using two-night 7-Dimensional Telescope (7DT) medium-band photometry obtained on March 23 and 24, 2024. The 7DT observations provide optical spectral sampling with 16 medium-band filters spanning 400--825 nm, enabling direct two-epoch comparisons. To remove satellite-trail contamination, we used an SSIM-based ResNet classifier (accuracy 0.97; F1 = 0.93) to exclude affected exposures. Subsequent photometry and two-epoch variability measurements yielded a working sample of 769 YSO candidates, among which we identified 110 variables ($\sim$14\%), including seven extreme cases with $|\Delta m_\lambda|>0.5$ mag. To describe the wavelength dependence of the variability, we compared five simple templates: extinction-like changes ($R_V =$ 3.1 and 5.5), a gray (wavelength-independent) change, and two spot-like toy models (hot and cold) implemented as two-temperature surface mixtures. The best-fit results are dominated by spot-like templates (37 cold-spot and 22 hot-spot objects), with 37 sources best matched by extinction-like templates and 14 by the gray template. The m650 excess fraction is higher in the hot-spot and gray templates than in the others. This could be compatible with more frequent line/veiling-related contributions in those groups, although the m650 excess is not a direct accretion diagnostic.

astro-ph.SR↗

arXiv2026

GriNNder: Breaking the Memory Capacity Wall in Full-Graph GNN Training with Storage Offloading

Full-graph training of graph neural networks (GNNs) is widely used as it enables direct validation of algorithmic improvements by preserving complete neighborhood information. However, it typically requires multiple GPUs or servers, incurring substantial hardware and inter-device communication costs. While existing single-server methods reduce infrastructure requirements, they remain constrained by GPU and host memory capacity as graph sizes increase. To address this limitation, we introduce GriNNder, which is the first work to leverage storage devices to enable full-graph training even with limited memory. Because modern NVMe SSDs offer multi-terabyte capacities and bandwidths exceeding 10 GB/s, they provide an appealing option when memory resources are scarce. Yet, directly applying storage-based methods from other domains fails to address the unique access patterns and data dependencies in full-graph GNN training. GriNNder tackles these challenges by structured storage offloading (SSO), a framework that manages the GPU-host-storage hierarchy through coordinated cache, (re)gather, and bypass mechanisms. To realize the framework, we devise (i) a partition-wise caching strategy for host memory that exploits the observation on cross-partition dependencies, (ii) a regathering strategy for gradient computation that eliminates redundant storage operations, and (iii) a lightweight partitioning scheme that mitigates the memory requirements of existing graph partitioners. In experiments performed over various models and datasets, GriNNder achieves up to 9.78x speedup over state-of-the-art baselines and throughput comparable to distributed systems, enabling previously infeasible large-scale full-graph training even on a single GPU.

cs.DC↗

arXiv2026

NAVIS: Concurrent Search and Update with Low Position-Seeking Overhead in On-SSD Graph-Based Vector Search

On-disk graph-based vector search (GVS) has become the dominant approach for serving large-scale vector databases at high recall, but prior systems struggle to sustain concurrent search and update throughput on high-dimensional workloads. We find the main cause of this in position seeking, a full graph traversal that every update performs to locate neighbors before linking the new vector into the graph. Position seeking is fundamentally heavier than a search query, and its cost is further amplified by two systemic limitations of current GVS systems, packed layouts that couple every edge fetch to a full vector load, and a static entrance graph whose entry points drift away from newly inserted regions as updates accumulate. We present NAVIS, an on-SSD GVS system that drives down position-seeking overhead through (i) a layout-supported selective vector read that breaks the packed-page coupling without losing its locality benefits, (ii) a dynamic lightweight entrance graph update mechanism that reuses traversal information already produced by concurrent updates, and (iii) an entrance graph-aware edgelist cache that concentrates capacity on high-reuse paths near refreshed entry points. Across multiple large-scale high-dimensional benchmarks, NAVIS enhances average insertion throughput by up to 2.74x and average concurrent search throughput by up to 1.37x while reducing average search latency by up to 25.26%.

cs.DC↗

arXiv2026

LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM

Lookup tables (LUTs) have recently gained attention as an alternative compute mechanism that maps input operands to precomputed results, eliminating the need for arithmetic logic. LUTs not only reduce logic complexity, but also naturally support diverse numerical precisions without requiring separate circuits for each bitwidth-an increasingly important feature in quantized DNNs. This creates a favorable tradeoff in PIM: memory capacity can be used in place of logic to increase computational throughput, aligning well with DRAM-PIM architectures that offer high bandwidth and easily available memory but limited logic density. In this work, we explore this capacity-computation tradeoff in LUT-based PIM designs, where memory capacity is traded for performance by packing multiple MAC operations into a single LUT lookup. Building on this insight, we propose LOCALUT, a PIM-based design for efficient low-bit quantized DNN inference using operation-packed LUTs. First, we observe that these LUTs contain extensive redundancy and introduce LUT canonicalization, which eliminates duplicate entries to reduce LUT size. Second, we propose reordering LUT, a lightweight auxiliary LUT that remaps weight vectors to their canonical form required by LUT canonicalization with a simple LUT lookup. Third, we propose LUT slice streaming, a novel execution strategy that exploits the DRAM-buffer hierarchy by streaming only relevant LUT columns into the buffer and reusing them across multiple weight vectors. Evaluated on a real system based on UPMEM devices, we demonstrate a geometric mean speedup of 1.82x across various numeric precisions and DNN models. We believe LOCALUT opens a path toward scalable, low-logic PIM designs tailored for LUT-based DNN inference. Our implementation of LOCALUT is available at https://github.com/AIS-SNU/LoCaLUT.

cs.AR↗

arXiv2026

AGIS: Fast Approximate Graph Pattern Mining with Structure-Informed Sampling

Approximate Graph Pattern Mining (AGPM) is essential for analyzing large-scale graphs where exact counting is computationally prohibitive. While there exist numerous sampling-based AGPM systems, they all rely on uniform sampling and overlook the underlying probability distribution. This limitation restricts their scalability to a broader range of patterns. In this paper, we introduce AGIS, an extremely fast AGPM system capable of counting arbitrary patterns from huge graphs. AGIS employs structure-informed neighbor sampling, a novel sampling technique that deviates from uniformness but allocates specific sampling probabilities based on the pattern structure. We first derive the ideal sampling distribution for AGPM and then present a practical method to approximate it. Furthermore, we develop a method that balances convergence speed and computational overhead, determining when to use the approximated distribution. Experimental results demonstrate that AGIS significantly outperforms the state-of-the-art AGPM system, achieving 28.5x geometric mean speedup and more than 100,000x speedup in specific cases. Furthermore, AGIS is the only AGPM system that scales to graphs with tens of billions of edges and robustly handles diverse patterns, successfully providing accurate estimates within seconds. We will open-source AGIS to encourage further research in this field.

cs.DS↗

arXiv2025

FlexiWalker: Extensible GPU Framework for Efficient Dynamic Random Walks with Runtime Adaptation

Dynamic random walks are fundamental to various graph analysis applications, offering advantages by adapting to evolving graph properties. Their runtime-dependent transition probabilities break down the pre-computation strategy that underpins most existing CPU and GPU static random walk optimizations. This leaves practitioners suffering from suboptimal frameworks and having to write hand-tuned kernels that do not adapt to workload diversity. To handle this issue, we present FlexiWalker, the first GPU framework that delivers efficient, workload-generic support for dynamic random walks. Our design-space study shows that rejection sampling and reservoir sampling are more suitable than other sampling techniques under massive parallelism. Thus, we devise (i) new high-performance kernels for them that eliminate global reductions, redundant memory accesses, and random-number generation. Given the necessity of choosing the best-fitting sampling strategy at runtime, we adopt (ii) a lightweight first-order cost model that selects the faster kernel per node at runtime. To enhance usability, we introduce (iii) a compile-time component that automatically specializes user-supplied walk logic into optimized building blocks. On various dynamic random walk workloads with real-world graphs, FlexiWalker outperforms the best published CPU/GPU baselines by geometric means of 73.44x and 5.91x, respectively, while successfully executing workloads that prior systems cannot support. We open-source FlexiWalker in https://github.com/AIS-SNU/FlexiWalker.

cs.DC↗

arXiv2025

Refined classification of YSOs and AGB stars by IR magnitudes, colors, and time-domain analysis with machine learning

We introduce a binary classification model, {\it the Double Filter Model}, utilizing various machine learning and deep learning methods to classify Young Stellar Objects (YSOs) and Asymptotic Giant Branch (AGB) stars. Since YSOs and AGB stars share similar infrared (IR) photometric characteristics due to comparable temperatures and the presence of circumstellar dust, distinguishing them is challenging and often leads to misclassification. While machine learning and deep learning techniques have helped reduce YSO-AGB misclassifications, achieving a reliable separation remains challenging. Given that YSOs and AGB stars exhibit distinct light curves resulting from different variability mechanisms, our Double Filter Model leverages light curve data to enhance classification accuracy. This approach uncovered YSOs and AGB stars that were misclassified in IR photometry and was validated against Taurus YSOs and spectroscopically confirmed AGB stars. We applied the model to the {\it Spitzer/IRAC Candidate YSO Catalog for the Inner Galactic Midplane} (SPICY) catalog for catalog refinement and identified potential AGB star contaminants.

astro-ph.SR↗

arXiv2025

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic

Low-bit floating-point (FP) formats, such as FP8, provide significant acceleration and memory savings in model training thanks to native hardware support on modern GPUs and NPUs. However, we analyze that FP8 quantization offers speedup primarily for large-dimensional matrix multiplications, while inherent quantization overheads diminish speedup when applied to low-rank adaptation (LoRA), which uses small-dimensional matrices for efficient fine-tuning of large language models (LLMs). To address this limitation, we propose FALQON, a novel framework that eliminates the quantization overhead from separate LoRA computational paths by directly merging LoRA adapters into an FP8-quantized backbone during fine-tuning. Furthermore, we reformulate the forward and backward computations for merged adapters to significantly reduce quantization overhead, and introduce a row-wise proxy update mechanism that efficiently integrates substantial updates into the quantized backbone. Experimental evaluations demonstrate that FALQON achieves approximately a 3$\times$ training speedup over existing quantized LoRA methods with a similar level of accuracy, providing a practical solution for efficient large-scale model fine-tuning. Moreover, FALQON's end-to-end FP8 workflow removes the need for post-training quantization, facilitating efficient deployment. Code is available at https://github.com/iamkanghyunchoi/falqon.

cs.LG↗

arXiv2025

PathWeaver: A High-Throughput Multi-GPU System for Graph-Based Approximate Nearest Neighbor Search

Graph-based Approximate Nearest Neighbor Search (ANNS) is widely adopted in numerous applications, such as recommendation systems, natural language processing, and computer vision. While recent works on GPU-based acceleration have significantly advanced ANNS performance, the ever-growing scale of datasets now demands efficient multi-GPU solutions. However, the design of existing works overlooks multi-GPU scalability, resulting in naive approaches that treat additional GPUs as a means to extend memory capacity for large datasets. This inefficiency arises from partitioning the dataset and independently searching for data points similar to the queries in each GPU. We therefore propose PathWeaver, a novel multi-GPU framework designed to scale and accelerate ANNS for large datasets. First, we propose pipelining-based path extension, a GPU-aware pipelining mechanism that reduces prior work's redundant search iterations by leveraging GPU-to-GPU communication. Second, we design ghost staging that leverages a representative dataset to identify optimal query starting points, reducing the search space for challenging queries. Finally, we introduce direction-guided selection, a data selection technique that filters irrelevant points early in the search process, minimizing unnecessary memory accesses and distance computations. Comprehensive evaluations across diverse datasets demonstrate that PathWeaver achieves 3.24$\times$ geomean speedup and up to 5.30$\times$ speedup on 95% recall rate over state-of-the-art multi-GPU-based ANNS frameworks.

cs.DC↗

arXiv2025

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

Multi-objective reinforcement learning (MORL) aims to optimize policies in the presence of conflicting objectives, where linear scalarization is commonly used to reduce vector-valued returns into scalar signals. While effective for certain preferences, this approach cannot capture fairness-oriented goals such as Nash social welfare or max-min fairness, which require nonlinear and non-additive trade-offs. Although several online algorithms have been proposed for specific fairness objectives, a unified approach for optimizing nonlinear welfare criteria in the offline setting-where learning must proceed from a fixed dataset-remains unexplored. In this work, we present FairDICE, the first offline MORL framework that directly optimizes nonlinear welfare objective. FairDICE leverages distribution correction estimation to jointly account for welfare maximization and distributional regularization, enabling stable and sample-efficient learning without requiring explicit preference weights or exhaustive weight search. Across multiple offline benchmarks, FairDICE demonstrates strong fairness-aware performance compared to existing baselines.

cs.LG↗

arXiv2025

Piccolo: Large-Scale Graph Processing with Fine-Grained In-Memory Scatter-Gather

Graph processing requires irregular, fine-grained random access patterns incompatible with contemporary off-chip memory architecture, leading to inefficient data access. This inefficiency makes graph processing an extremely memory-bound application. Because of this, existing graph processing accelerators typically employ a graph tiling-based or processing-in-memory (PIM) approach to relieve the memory bottleneck. In the tiling-based approach, a graph is split into chunks that fit within the on-chip cache to maximize data reuse. In the PIM approach, arithmetic units are placed within memory to perform operations such as reduction or atomic addition. However, both approaches have several limitations, especially when implemented on current memory standards (i.e., DDR). Because the access granularity provided by DDR is much larger than that of the graph vertex property data, much of the bandwidth and cache capacity are wasted. PIM is meant to alleviate such issues, but it is difficult to use in conjunction with the tiling-based approach, resulting in a significant disadvantage. Furthermore, placing arithmetic units inside a memory chip is expensive, thereby supporting multiple types of operation is thought to be impractical. To address the above limitations, we present Piccolo, an end-to-end efficient graph processing accelerator with fine-grained in-memory random scatter-gather. Instead of placing expensive arithmetic units in off-chip memory, Piccolo focuses on reducing the off-chip traffic with non-arithmetic function-in-memory of random scatter-gather. To fully benefit from in-memory scatter-gather, Piccolo redesigns the cache and MHA of the accelerator such that it can enjoy both the advantage of tiling and in-memory operations. Piccolo achieves a maximum speedup of 3.28$\times$ and a geometric mean speedup of 1.62$\times$ across various and extensive benchmarks.

cs.AR↗

arXiv2025

A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs

The computational and memory demands of large language models for generative inference present significant challenges for practical deployment. One promising solution targeting offline inference is offloading-based batched inference, which extends the GPU's memory hierarchy with host memory and storage. However, it often suffers from substantial I/O overhead, primarily due to the large KV cache sizes that scale with batch size and context window length. In this paper, we introduce HILOS, a framework that boosts offline inference throughput using near-storage processing. The core of HILOS is attention near storage, which offloads memory-intensive attention operations to near-storage accelerators, reducing traffic across the system interconnect. Building on attention near storage, HILOS incorporates three additional optimizations. First, cooperative X-cache minimizes KV cache I/O by exploiting available host resources after offloading. Second, delayed KV cache writeback hides storage write latency and mitigates storage write amplification. Finally, a memory-efficient attention accelerator sustains high throughput for long sequences within the resource constraints of NSP devices. We implemented and evaluated HILOS on a real system equipped with 16 SmartSSDs. Compared to state-of-the-art offloading-based inference frameworks, HILOS achieves up to 7.86x throughput while reducing energy consumption by up to 85\%. The source code for HILOS is available at https://github.com/hongsunjang/HILOS.

cs.AR↗

arXiv2024

DeepClair: Utilizing Market Forecasts for Effective Portfolio Selection

Utilizing market forecasts is pivotal in optimizing portfolio selection strategies. We introduce DeepClair, a novel framework for portfolio selection. DeepClair leverages a transformer-based time-series forecasting model to predict market trends, facilitating more informed and adaptable portfolio decisions. To integrate the forecasting model into a deep reinforcement learning-driven portfolio selection framework, we introduced a two-step strategy: first, pre-training the time-series model on market data, followed by fine-tuning the portfolio selection architecture using this model. Additionally, we investigated the optimization technique, Low-Rank Adaptation (LoRA), to enhance the pre-trained forecasting model for fine-tuning in investment scenarios. This work bridges market forecasting and portfolio selection, facilitating the advancement of investment strategies.

cs.CE↗