AI总结
本文提出Genflow Ad Studio,一种复合AI架构,通过品牌DNA提取模块和对抗性多代理质量控制循环,提高了品牌一致的视频生成效率,将合规率从42%提升到89%。
Comments6 pages, 2 figures, 2 tables. Accepted to the ACM Conference on AI and Agentic Systems (CAIS '26). Includes demo video and code repository links
Journal refACM Conference on AI and Agentic Systems (CAIS '26), May 26-29, 2026, San Jose, CA, USA
Video Reconstruction using Diffusion-based Image-to-Video Generation with Trajectory Guidance
基于扩散模型的图像到视频生成与轨迹引导的视频重建
Stelio Bompai, Ioannis Kontopoulos, Giannis Spiliopoulos, Dimitris Zissis, Konstantinos Tserpes
机构
*
Department of Electrical and Computer Engineering, National Technical University of Athens, Greece(电气与计算机工程系,希腊国家技术大学雅典分校)
;
Department of Product and Systems Design Engineering, University of the Aegean, Syros, Greece(产品与系统设计工程系,爱琴海大学锡罗斯分校)
CommentsAccepted at the 1st Workshop on Multi-Sensor Trajectory Knowledge Discovery and Extraction (MuseKDE 2026), co-located with the 27th IEEE International Conference on Mobile Data Management (IEEE MDM 2026)
Transformers for Learning on Noisy and Task-Level Manifolds: Approximation and Generalization Insights
用于噪声和任务级流形学习的Transformer:近似和泛化见解
Zhaiming Shen, Alex Havrilla, Rongjie Lai, Alexander Cloninger, Wenjing Liao
机构
*
School of Mathematics, Georgia Institute of Technology(佐治亚理工学院数学系)
;
Department of Mathematics, Purdue University(普渡大学数学系)
;
Department of Mathematics and Halicioğlu Data Science Institute, University of California, San Diego(加州大学圣地亚哥分校数学系和Halicioğlu数据科学研究所)