분류 전체보기349 [2025-2] 김지원 - Anchors: High-Precision Model-Agnostic Explanations 논문 소개: “LIME의 불안정성을 보완. ‘조건문(anchor)’ 형태로 국소적 설명을 안정적으로 제공하는 논문”, 2018년 AAAI 학회에서 발표됨인용 수: 2025.11.01 기준 3165회논문 링크: https://ojs.aaai.org/index.php/aaai/article/view/11491 Anchors: High-Precision Model-Agnostic Explanations | Proceedings of the AAAI Conference on Artificial Intelligence ojs.aaai.orgAnchors: 닻→ 조건문 기반으로 모델을 안정적으로 설명하기 위해 붙잡아 두는 역할 Abstract저자는 anchors라고 불리는 high-precision rules를 가.. 2025. 11. 2. [2025-2] 백승우 - UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action UltraCUA: A Foundation Model for Computer Use Agents with Hybrid ActionMultimodal agents for computer use rely exclusively on primitive actions (click, type, scroll) that require accurate visual grounding and lengthy execution chains, leading to cascading failures and performance bottlenecks. While other agents leverage richarxiv.org 2025. 10. 29. [2025-2] 백승우 - Agent Learning via Early Experience Agent Learning via Early ExperienceA long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many enviarxiv.org 2025. 10. 15. [2025-2] 박제우 - ANOMALYCLIP: OBJECT-AGNOSTIC PROMPT LEARNING FOR ZERO-SHOT ANOMALY DETECTION https://arxiv.org/abs/2310.18961 AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly DetectionZero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due to various concerns, eg, data privaarxiv.org 0. Abstract제로샷 이상탐지(ZS.. 2025. 9. 27. 이전 1 2 3 4 ··· 88 다음
