전체 글348 [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. [2025-2] 최민서 - 3D-HLDM: Human-Guided Latent Diffusion Model to Improve Microvascular Invasion Prediction in Hepatocellular Carcinoma [논문링크] https://ieeexplore.ieee.org/document/10635195/authors#authors 3D-HLDM: Human-Guided Latent Diffusion Model to Improve Microvascular Invasion Prediction in Hepatocellular CarcinomaMicrovascular invasion (MVI) is a critical risk factor for survival in patients with Hepatocellular Carcinoma. The presurgical prediction of MVI is clinically important and crucial for surgical and treatment plan.. 2025. 9. 18. 이전 1 2 3 4 ··· 87 다음
