제목, 요약, 본문을 검색해 흩어진 정보를 연결하세요.
arXiv:2610.32720v1 발표 유형: 신규 초록: 저궤도(LEO) 위성 메가컨스텔레이션은 지연 시간이 중요한 지구 중심 응용을 위한 궤도 기반 엣지 컴퓨팅을 가능하게 하지만, 위성의 운동으로 인해 시선 통신 창은 단 몇 분으로 압축된다. 논리적 지리적 근접성을 유지하기 위해 ‘가상 정지성(VS)’이라는 패러다임에 따라, 애플리케이션은 컨스텔레이션 내에서 지나가는 위성들 사이를 지속적으로 이동해야 한다. 전통적인 라이브 마이그레이션 메커니즘은 개별적으로 시작된 이동이나 복제는 최적화하지만, 궤도 운동이 요구하는 연속적인 호스트 간 핸드오프는 처리하지 못한다. 우리는 라이브 마이그레이션을 정상 상태 실행 모델로 재정립하고, 새로운 가상 정지성 런타임 패러다임을 도입한다. 또한 우리는 연속 마이그레이션의 실현 가능성을 공식화한다…
arXiv:2610.32027v1 Announce Type: new Abstract: HPC clusters are shared among many projects, each holding an allocation of node-hours, and ensuring fairness is becoming harder. Foundation models workflows and automated pipelines have made job submissions bursty and concentrated among a few heavy users, so occasional users absorb queueing delays created by frequent ones, with no indication of how long their jobs will wait. Existing schedulers either forget past usage, protect only the job at the head of the queue, or assume that running jobs can be preempted. We propose HyDRA, a Hybrid Deadline and Ranking-Aware scheduler that enforces fairness among users while bounding the queue wait of every job. HyDRA assigns each job a deadline on arrival based on its size, the priorities of its projec
번역 대기 중 · 원문 표시 · enarXiv:2610.32022v1 Announce Type: new Abstract: Intent recognition in human-robot interaction requires agents to resolve ambiguous natural language instructions by inferring the speaker's underlying goals. Research has increasingly focused on two notable paradigms for addressing this task: structured symbolic reasoning and multimodal input enrichment. However, it remains unclear whether enrichment-based methods provide benefit in settings where the ambiguity concerns unstated human intent rather than missing observable scene information. In this paper, we present a comparative and diagnostic study benchmarking FISER - a framework utilizing structured social and embodied reasoning - against CEMIR (Context-Enriched Multimodal Intent Recognition), a method that performs multimodal enrichment
번역 대기 중 · 원문 표시 · enarXiv:2610.31701v1 Announce Type: new Abstract: Enterprise customer journeys are shaped not only by product experiences and marketing, but also by recurring resource-allocation decisions. In B2B go-to-market (GTM) organizations, territory carving determines which accounts receive seller coverage, which seller-account relationships are preserved, and how limited field capacity is distributed. Yet the process often remains manual, making it difficult to compare opportunities, value continuity, and evaluate tradeoffs among growth, balance, capacity, and feasibility. We present a production decision system for tradeoff-aware customer-to-seller allocation in enterprise GTM planning. It integrates three components: a multidimensional account-value layer that combines predictive signals to score
번역 대기 중 · 원문 표시 · enarXiv:2610.31702v1 Announce Type: new Abstract: Indoor radio map estimation (RME) is essential for wireless applications such as coverage planning, localization, and network deployment. However, most existing methods follow a supervised learning paradigm that requires costly labeled data and task-specific model training. Moreover, indoor environments involve privacy-sensitive information, such as building layouts and structures, that often cannot be centralized. To address these challenges, we make the first attempt to formulate indoor RME as a collaborative in-context learning (ICL) problem. We propose Poly-Ripple, a framework in which multiple clients perform ICL using large autoregressive vision models (LAVMs) without model updates. Each client is prompted by its private demonstrations
번역 대기 중 · 원문 표시 · enarXiv:2610.31808v1 Announce Type: new Abstract: Patronizing and condescending language (PCL) is a form of harmful language that belittles and assumes pity for vulnerable groups, reinforcing negative societal stereotypes. However, unlike overt hate speech, it is often difficult to detect, even for human judges. This paper proposes a system for the automated detection of PCL. Our first approach uses static word embeddings and a convolutional neural network for classification, while our second approach uses pre-trained BERT embeddings fine-tuned for the PCL task. Our second approach was considerably more successful, and achieved an F1 score of 0.528 over the development set.
번역 대기 중 · 원문 표시 · enarXiv:2610.31937v1 발표 유형: 신규 초록: 현대의 대규모 언어 모델(LLM)은 신중하게 조율된 다단계 대화를 통해 안전 메커니즘을 점진적으로 우회하는 공격에 여전히 취약합니다. 그러나 기존의 많은 레드팀 접근법은 휴리스틱에 의존하거나 강력한 가정을 도입함으로써 완전한 블랙박스 환경에서의 적용 가능성을 제한합니다. 우리는 이러한 한계를 해소하기 위해 $M^3$이라는 자동화된 레드팀 프레임워크를 제안하며, 이는 다단계 잠금 해제를 유한 시간 horizon의 마르코프 결정 과정(MDP)으로 형식화합니다. $M^3$에서는 공격자 LLM이 상태 LLM이 생성한 간결한 내부 상태를 기반으로 작동하면서 타깃 LLM과 상호작용합니다. 두 가지 벤치마크와 여섯 개의 타깃 모델을 대상으로 한 실험에서, $M^3$은 공격 성공률(ASR) 측면에서 최첨단 다단계 레드팀 방법들을 일관되게 능가했습니다, a
arXiv:2610.31716v1 Announce Type: new Abstract: We examine how closely pretrained LeWorldModel (LeWM) reproduces the effects of small action changes. Using matched simulator and model responses, we measure action sensitivity with Gram matrices at three perturbation scales. Across nearly a thousand states from Reacher and OGBench Cube, the most sensitive action directions differ by median angles of about $36^\circ$ and $42^\circ$, respectively, at the smallest scale. Increasing the perturbation tenfold reduces median normalized Gram discrepancy by roughly 70\% on Reacher and 47\% on Cube. Geometry measured in pixels and embeddings varies more across scales than the chosen physical-state geometry. On held-out directions, environment Grams achieve median embedding response errors of 17\% and
번역 대기 중 · 원문 표시 · enarXiv:2610.31704v1 Announce Type: new Abstract: Non-Destructive Inspection (NDI) is a cornerstone of modern quality assurance, critical for ensuring the safety and reliability of infrastructure and manufactured components without causing damage. This paper presents a comprehensive review of the current NDI landscape, analyzing the field through four distinct lenses, namely, computational algorithms, physical techniques, industrial applications, and research objectives. We synthesize a broad range of academic literature to illustrate the rapid evolution from manual, analog interpretation to a digitized, data-centric paradigm known as NDE 4.0. Our analysis highlights the dominance of ultrasound and visual inspection as primary physical techniques, while revealing a significant shift toward d
번역 대기 중 · 원문 표시 · enarXiv:2610.31718v1 발표 유형: 신규 초록: 금융 거래 네트워크는 자연스럽게 다중그래프로 표현되며, 동일한 계좌 쌍 간의 반복된 거래는 서로 다른 엣지로 모델링된다. 최근 제안된 다중그래프 신경망 아키텍처들은 이러한 구조를 명시적으로 활용하여 자금세탁방지(AML) 작업에서 뛰어난 성능을 달성한다. 그러나 탐지를 회피하기 위해 거래 구조를 조작하는 적대적 공격에 대한 이들의 내구성은 아직 거의 연구되지 않았다. 우리는 노드-엣지 인시던스 행렬을 이용한 다중그래프 신경망의 구조적 공격 및 적대적 학습을 위한 최초의 확장 가능한 프레임워크를 제시하며, 이러한 다중그래프 위에서 구조적 변동을 최적화하기 위해 투영된 경사하강법과 투영된 무작위 블록 좌표 하강법을 적용한다.
arXiv:2610.31722v1 Announce Type: new Abstract: Microservice systems have become a dominant architecture for large-scale cloud applications, enabling rapid deployment and elastic scaling. However, ensuring the reliability and availability of microservice systems critically relies on effective anomaly detection, as failures and performance anomalies can quickly propagate across services and severely impact end-to-end system behavior. Existing multimodal anomaly detection approaches for microservice systems often struggle with two fundamental limitations: (i) the neglect of modality-specific characteristics in favor of cross-modality fusion, and (ii) the "identity-shortcut" problem that affects the feature reconstruction process. To address these issues, we propose LLMMAD, an autoregressive
번역 대기 중 · 원문 표시 · en