Searcharxiv⌕ Search

arXiv subjects

Jaewon Jung

Publications and source records attributed to Jaewon Jung.

18 recordsLinked to original sources
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

MMA-Former: Multi-Window Mixture-of-Head Attention Transformer for Adaptive PNI Prediction in 3D MRI

Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. Non-invasive prediction from 3D MRI is challenging, demanding models that efficiently capture both fine-grained details and global context. We propose the Multi-window Mixture-of-Head Attention Transformer (MMA-Former), a novel end-to-end 3D architecture featuring a Coarse-Fine Transformer (CFT) structure for parallel multi-scale feature extraction. We advance this structure by integrating a novel Window-Specific Mixture-of-Head attention (WS-MoH) mechanism. Unlike standard Multi-Head Self Attention (MSA), WS-MoH generates a representation for each 3D window and dynamically routes the entire window to specialized or common attention heads. This enables spatially adaptive feature extraction tailored to the local context of each window, enhancing specialization and reducing redundancy without increasing parameters. Evaluated on a retrospective dataset of 168 T1-weighted MRI scans, MMA-Former achieved an AUC of 0.752, outperforming other 3D architectures, including the best CNN (AUC of 0.708) and Transformer baselines (AUC of 0.681).

cs.CV↗
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

NeoNet: An End-to-End 3D MRI-Based Deep Learning Framework for Non-Invasive Prediction of Perineural Invasion via Generation-Driven Classification

Minimizing invasive diagnostic procedures to reduce the risk of patient injury and infection is a central goal in medical imaging. And yet, noninvasive diagnosis of perineural invasion (PNI), a critical prognostic factor involving infiltration of tumor cells along the surrounding nerve, still remains challenging, due to the lack of clear and consistent imaging criteria criteria for identifying PNI. To address this challenge, we present NeoNet, an integrated end-to-end 3D deep learning framework for PNI prediction in cholangiocarcinoma that does not rely on predefined image features. NeoNet integrates three modules: (1) NeoSeg, utilizing a Tumor-Localized ROI Crop (TLCR) algorithm; (2) NeoGen, a 3D Latent Diffusion Model (LDM) with ControlNet, conditioned on anatomical masks to generate synthetic image patches, specifically balancing the dataset to a 1:1 ratio; and (3) NeoCls, the final prediction module. For NeoCls, we developed the PNI-Attention Network (PattenNet), which uses the frozen LDM encoder and specialized 3D Dual Attention Blocks (DAB) designed to detect subtle intensity variations and spatial patterns indicative of PNI. In 5-fold cross-validation, NeoNet outperformed baseline 3D models and achieved the highest performance with a maximum AUC of 0.7903.

cs.CV↗
arXiv2026

LUMINA: Laplacian-Unifying Mechanism for Interpretable Neurodevelopmental Analysis via Quad-Stream GCN

Functional Magnetic Resonance Imaging(fMRI) has now become a classic way for measuring brain activity, and recent trend is shifting toward utilizing fMRI brain data for AI-driven diagnosis. Given that the brain functions as not a discrete but interconnected whole, Graph-based architectures represented by Graph Convolutional Network(GCN) has emerged as a dominant framework for such task, since they are capable of treating ROIs as dynamically interconnected nodes and extracting relational architecture between them. Ironically, however, it is the very nature of GCN's architecture that acts as an obstacle to its performance. The mathematical foundation of GCN, effective for capturing global regularities, acts as a tradeoff; by smoothing features across the connected nodes repeatedly, traditional GCN tend to blur out the contrastive dynamics that might be crucial in identifying certain neurological disorders. In order to break through this structural bottleneck, we propose LUMINA, a Laplacian-Unifying Mechanism for Interpretable Neurodevelopmental Analysis. Our model is a Quad-Stream GCN that employs a bipolar RELU activation and a dual-spectrum graph Laplacian filtering mechanism, thereby capturing heterogeneous dynamics that were often blurred out in conventional GCN. By doing so, we can preserve the diverse range and characteristics of neural connections in each fMRI data. Through 5-fold cross validation on the ADHD200(N=144) and ABIDE(N=579) dataset, LUMINA demonstrates stable diagnostic performance in two of the most critical neurodevelopmental disorder in childhood, ADHD and ASD, outperforming existing models with an accuracy of 84.66% and 88.41% each.

cs.LG↗
arXiv2026

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↗
arXiv2025

LLM-guided Plan and Retrieval: A Strategic Alignment for Interpretable User Satisfaction Estimation in Dialogue

Understanding user satisfaction with conversational systems, known as User Satisfaction Estimation (USE), is essential for assessing dialogue quality and enhancing user experiences. However, existing methods for USE face challenges due to limited understanding of underlying reasons for user dissatisfaction and the high costs of annotating user intentions. To address these challenges, we propose PRAISE (Plan and Retrieval Alignment for Interpretable Satisfaction Estimation), an interpretable framework for effective user satisfaction prediction. PRAISE operates through three key modules. The Strategy Planner develops strategies, which are natural language criteria for classifying user satisfaction. The Feature Retriever then incorporates knowledge on user satisfaction from Large Language Models (LLMs) and retrieves relevance features from utterances. Finally, the Score Analyzer evaluates strategy predictions and classifies user satisfaction. Experimental results demonstrate that PRAISE achieves state-of-the-art performance on three benchmarks for the USE task. Beyond its superior performance, PRAISE offers additional benefits. It enhances interpretability by providing instance-level explanations through effective alignment of utterances with strategies. Moreover, PRAISE operates more efficiently than existing approaches by eliminating the need for LLMs during the inference phase.

cs.CL↗
arXiv2024

Application of zero-noise extrapolation-based quantum error mitigation to a silicon spin qubit

As quantum computing advances towards practical applications, reducing errors remains a crucial frontier for developing near-term devices. Errors in the quantum gates and quantum state readout could result in noisy circuits, which would prevent the acquisition of the exact expectation values of the observables. Although ultimate robustness to errors is known to be achievable by quantum error correction-based fault-tolerant quantum computing, its successful implementation demands large-scale quantum processors with low average error rates that are not yet widely available. In contrast, quantum error mitigation (QEM) offers more immediate and practical techniques, which do not require extensive resources and can be readily applied to existing quantum devices to improve the accuracy of the expectation values. Here, we report the implementation of a zero-noise extrapolation-based error mitigation technique on a silicon spin qubit platform. This technique has recently been successfully demonstrated for other platforms such as superconducting qubits, trapped-ion qubits, and photonic processors. We first explore three methods for amplifying noise on a silicon spin qubit: global folding, local folding, and pulse stretching, using a standard randomized benchmarking protocol. We then apply global folding-based zero-noise extrapolation to the state tomography and achieve a state fidelity of 99.96% (98.52%), compared to the unmitigated fidelity of 75.82% (82.16%) for different preparation states. The results show that the zero-noise extrapolation technique is a versatile approach that is generally adaptable to quantum computing platforms with different noise characteristics through appropriate noise amplification methods.

quant-ph↗
arXiv2024

GraNNDis: Efficient Unified Distributed Training Framework for Deep GNNs on Large Clusters

Graph neural networks (GNNs) are one of the rapidly growing fields within deep learning. While many distributed GNN training frameworks have been proposed to increase the training throughput, they face three limitations when applied to multi-server clusters. 1) They suffer from an inter-server communication bottleneck because they do not consider the inter-/intra-server bandwidth gap, a representative characteristic of multi-server clusters. 2) Redundant memory usage and computation hinder the scalability of the distributed frameworks. 3) Sampling methods, de facto standard in mini-batch training, incur unnecessary errors in multi-server clusters. We found that these limitations can be addressed by exploiting the characteristics of multi-server clusters. Here, we propose GraNNDis, a fast distributed GNN training framework for multi-server clusters. Firstly, we present Flexible Preloading, which preloads the essential vertex dependencies server-wise to reduce the low-bandwidth inter-server communications. Secondly, we introduce Cooperative Batching, which enables memory-efficient, less redundant mini-batch training by utilizing high-bandwidth intra-server communications. Thirdly, we propose Expansion-aware Sampling, a cluster-aware sampling method, which samples the edges that affect the system speedup. As sampling the intra-server dependencies does not contribute much to the speedup as they are communicated through fast intra-server links, it only targets a server boundary to be sampled. Lastly, we introduce One-Hop Graph Masking, a computation and communication structure to realize the above methods in multi-server environments. We evaluated GraNNDis on multi-server clusters, and it provided significant speedup over the state-of-the-art distributed GNN training frameworks. GraNNDis is open-sourced at https://github.com/AIS-SNU/GraNNDis_Artifact to facilitate its use.

cs.LG↗
arXiv2024

Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders

Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to generate responses on illegal or sensitive topics, posing a significant threat to their safe and ethical use. Existing approaches attempt to address this issue using classification models, but they have several drawbacks. With the increasing complexity of unsafe prompts, similarity search-based techniques that identify specific features of unsafe prompts provide a more robust and effective solution to this evolving problem. This paper investigates the potential of sentence encoders to distinguish safe from unsafe prompts, and the ability to classify various unsafe prompts according to a safety taxonomy. We introduce new pairwise datasets and the Categorical Purity (CP) metric to measure this capability. Our findings reveal both the effectiveness and limitations of existing sentence encoders, proposing directions to improve sentence encoders to operate as more robust safety detectors. Our code is available at https://github.com/JwdanielJung/Safe-Embed.

cs.CL↗
arXiv2024

Autonomous Ground Navigation in Highly Constrained Spaces: Lessons learned from The 3rd BARN Challenge at ICRA 2024

The 3rd BARN (Benchmark Autonomous Robot Navigation) Challenge took place at the 2024 IEEE International Conference on Robotics and Automation (ICRA 2024) in Yokohama, Japan and continued to evaluate the performance of state-of-the-art autonomous ground navigation systems in highly constrained environments. Similar to the trend in The 1st and 2nd BARN Challenge at ICRA 2022 and 2023 in Philadelphia (North America) and London (Europe), The 3rd BARN Challenge in Yokohama (Asia) became more regional, i.e., mostly Asian teams participated. The size of the competition has slightly shrunk (six simulation teams, four of which were invited to the physical competition). The competition results, compared to last two years, suggest that the field has adopted new machine learning approaches while at the same time slightly converged to a few common practices. However, the regional nature of the physical participants suggests a challenge to promote wider participation all over the world and provide more resources to travel to the venue. In this article, we discuss the challenge, the approaches used by the three winning teams, and lessons learned to direct future research and competitions.

cs.RO↗
arXiv2024

Pipette: Automatic Fine-grained Large Language Model Training Configurator for Real-World Clusters

Training large language models (LLMs) is known to be challenging because of the huge computational and memory capacity requirements. To address these issues, it is common to use a cluster of GPUs with 3D parallelism, which splits a model along the data batch, pipeline stage, and intra-layer tensor dimensions. However, the use of 3D parallelism produces the additional challenge of finding the optimal number of ways on each dimension and mapping the split models onto the GPUs. Several previous studies have attempted to automatically find the optimal configuration, but many of these lacked several important aspects. For instance, the heterogeneous nature of the interconnect speeds is often ignored. While the peak bandwidths for the interconnects are usually made equal, the actual attained bandwidth varies per link in real-world clusters. Combined with the critical path modeling that does not properly consider the communication, they easily fall into sub-optimal configurations. In addition, they often fail to consider the memory requirement per GPU, often recommending solutions that could not be executed. To address these challenges, we propose Pipette, which is an automatic fine-grained LLM training configurator for real-world clusters. By devising better performance models along with the memory estimator and fine-grained individual GPU assignment, Pipette achieves faster configurations that satisfy the memory constraints. We evaluated Pipette on large clusters to show that it provides a significant speedup over the prior art. The implementation of Pipette is available at https://github.com/yimjinkyu1/date2024_pipette.

cs.DC↗
arXiv2024

PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor

Adversarial robustness of the neural network is a significant concern when it is applied to security-critical domains. In this situation, adversarial distillation is a promising option which aims to distill the robustness of the teacher network to improve the robustness of a small student network. Previous works pretrain the teacher network to make it robust against the adversarial examples aimed at itself. However, the adversarial examples are dependent on the parameters of the target network. The fixed teacher network inevitably degrades its robustness against the unseen transferred adversarial examples which target the parameters of the student network in the adversarial distillation process. We propose PeerAiD to make a peer network learn the adversarial examples of the student network instead of adversarial examples aimed at itself. PeerAiD is an adversarial distillation that trains the peer network and the student network simultaneously in order to specialize the peer network for defending the student network. We observe that such peer networks surpass the robustness of the pretrained robust teacher model against adversarial examples aimed at the student network. With this peer network and adversarial distillation, PeerAiD achieves significantly higher robustness of the student network with AutoAttack (AA) accuracy by up to 1.66%p and improves the natural accuracy of the student network by up to 4.72%p with ResNet-18 on TinyImageNet dataset. Code is available at https://github.com/jaewonalive/PeerAiD.

cs.LG↗
arXiv2024

Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System

The recent huge advance of Large Language Models (LLMs) is mainly driven by the increase in the number of parameters. This has led to substantial memory capacity requirements, necessitating the use of dozens of GPUs just to meet the capacity. One popular solution to this is storage-offloaded training, which uses host memory and storage as an extended memory hierarchy. However, this obviously comes at the cost of storage bandwidth bottleneck because storage devices have orders of magnitude lower bandwidth compared to that of GPU device memories. Our work, Smart-Infinity, addresses the storage bandwidth bottleneck of storage-offloaded LLM training using near-storage processing devices on a real system. The main component of Smart-Infinity is SmartUpdate, which performs parameter updates on custom near-storage accelerators. We identify that moving parameter updates to the storage side removes most of the storage traffic. In addition, we propose an efficient data transfer handler structure to address the system integration issues for Smart-Infinity. The handler allows overlapping data transfers with fixed memory consumption by reusing the device buffer. Lastly, we propose accelerator-assisted gradient compression/decompression to enhance the scalability of Smart-Infinity. When scaling to multiple near-storage processing devices, the write traffic on the shared channel becomes the bottleneck. To alleviate this, we compress the gradients on the GPU and decompress them on the accelerators. It provides further acceleration from reduced traffic. As a result, Smart-Infinity achieves a significant speedup compared to the baseline. Notably, Smart-Infinity is a ready-to-use approach that is fully integrated into PyTorch on a real system. We will open-source Smart-Infinity to facilitate its use.

cs.AR↗
arXiv2023

Pipe-BD: Pipelined Parallel Blockwise Distillation

Training large deep neural network models is highly challenging due to their tremendous computational and memory requirements. Blockwise distillation provides one promising method towards faster convergence by splitting a large model into multiple smaller models. In state-of-the-art blockwise distillation methods, training is performed block-by-block in a data-parallel manner using multiple GPUs. To produce inputs for the student blocks, the teacher model is executed from the beginning until the current block under training. However, this results in a high overhead of redundant teacher execution, low GPU utilization, and extra data loading. To address these problems, we propose Pipe-BD, a novel parallelization method for blockwise distillation. Pipe-BD aggressively utilizes pipeline parallelism for blockwise distillation, eliminating redundant teacher block execution and increasing per-device batch size for better resource utilization. We also extend to hybrid parallelism for efficient workload balancing. As a result, Pipe-BD achieves significant acceleration without modifying the mathematical formulation of blockwise distillation. We implement Pipe-BD on PyTorch, and experiments reveal that Pipe-BD is effective on multiple scenarios, models, and datasets.

cs.LG↗
arXiv2023

Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression

In training of modern large natural language processing (NLP) models, it has become a common practice to split models using 3D parallelism to multiple GPUs. Such technique, however, suffers from a high overhead of inter-node communication. Compressing the communication is one way to mitigate the overhead by reducing the inter-node traffic volume; however, the existing compression techniques have critical limitations to be applied for NLP models with 3D parallelism in that 1) only the data parallelism traffic is targeted, and 2) the existing compression schemes already harm the model quality too much. In this paper, we present Optimus-CC, a fast and scalable distributed training framework for large NLP models with aggressive communication compression. Optimus-CC differs from existing communication compression frameworks in the following ways: First, we compress pipeline parallel (inter-stage) traffic. In specific, we compress the inter-stage backpropagation and the embedding synchronization in addition to the existing data-parallel traffic compression methods. Second, we propose techniques to avoid the model quality drop that comes from the compression. We further provide mathematical and empirical analyses to show that our techniques can successfully suppress the compression error. Lastly, we analyze the pipeline and opt to selectively compress those traffic lying on the critical path. This further helps reduce the compression error. We demonstrate our solution on a GPU cluster, and achieve superior speedup from the baseline state-of-the-art solutions for distributed training without sacrificing the model quality.

cs.LG↗
arXiv2022

A study on some approximations on the average number of the LLL bases in higher dimensions

There is a result related to the average number of the $(δ, η)$-LLL bases in dimension $n$ in theoretical sense but the formula seems to be complicated and computing in high dimension takes a long time. In practical sense, we suggest some approximations which can be computed by just storing some constants and computing relatively simple exponential functions.

math.NT↗
arXiv2019

Visual Relationship Detection with Language prior and Softmax

Visual relationship detection is an intermediate image understanding task that detects two objects and classifies a predicate that explains the relationship between two objects in an image. The three components are linguistically and visually correlated (e.g. "wear" is related to "person" and "shirt", while "laptop" is related to "table" and "on") thus, the solution space is huge because there are many possible cases between them. Language and visual modules are exploited and a sophisticated spatial vector is proposed. The models in this work outperformed the state of arts without costly linguistic knowledge distillation from a large text corpus and building complex loss functions. All experiments were only evaluated on Visual Relationship Detection and Visual Genome dataset.

cs.CV↗