Multi-Modal34 [2026-1] 정재훈 - Multimodal UnsupervisedImage-to-Image Translation https://arxiv.org/pdf/1804.04732 1. Introduction - 기존 모델의 한계기존에 존재한 CycleGAN을 비롯한 모델들은 입력과 출력이 1:1로 대응되어야 하는 한계점을 가짐 - 현실의 Multimodality 반영 불가현실을 모사하는 것에는 한가지 정답이 아닌 다양한 정답지가 있을 수 있으나 현재 모델은 결정론적인 함수의 형태가 많음. 위의 한계점을 극복한 MUNIT의 모델을 연구팀은 제안하고자 함. 2. Multimodal Unsupervised Image-to-image Translation1. Assumtionxi ∈ Xi 이고, x1 = G_1 (c, s1) x2 = G_2 (c, s2)라 하자.여기서 c는 content code s는 style code를 의.. 2026. 5. 16. [2026-1] 백승우 - Agentic Reward Modeling: Verifying GUI Agent via Online Proactive Interaction Agentic Reward Modeling: Verifying GUI Agent via Online Proactive InteractionReinforcement learning with verifiable rewards (RLVR) is pivotal for the continuous evolution of GUI agents, yet existing evaluation paradigms face significant limitations. Rule-based methods suffer from poor scalability and cannot handle open-ended tasks,arxiv.org 2026. 3. 24. [2026-1] 강민정, 염제원 - GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks Paperhttps://arxiv.org/abs/2510.04374 GDPval: Evaluating AI Model Performance on Real-World Economically Valuable TasksWe introduce GDPval, a benchmark evaluating AI model capabilities on real-world economically valuable tasks. GDPval covers the majority of U.S. Bureau of Labor Statistics Work Activities for 44 occupations across the top 9 sectors contributing to U.S. GDParxiv.orgArticlehttps://.. 2026. 3. 20. [2026-1] 백승우 - AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines https://arxiv.org/abs/2602.14296 AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State MachinesThe performance of autonomous Web GUI agents heavily relies on the quality and quantity of their training data. However, a fundamental bottleneck persists: collecting interaction trajectories from real-world websites is expensive and difficult to verify. Tarxiv.org 2026. 3. 10. 이전 1 2 3 4 5 ··· 9 다음
