arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Georgia Institute of Technology(佐治亚理工学院)

2026-01-01 至 2026-01-01 共收录 5
2512.24948 2026-01-01 cs.CV cs.LG

ProDM: Synthetic Reality-driven Property-aware Progressive Diffusion Model for Coronary Calcium Motion Correction in Non-gated Chest CT

ProDM:合成现实驱动的属性感知渐进扩散模型用于非门控胸部CT中的冠状动脉钙运动校正

Xinran Gong, Gorkem Durak, Halil Ertugrul Aktas, Vedat Cicek, Jinkui Hao, Ulas Bagci, Nilay S. Shah, Bo Zhou

机构 * Department of Radiology, Northwestern University, Chicago, IL, USA College of Computing, Georgia Institute of Technology, Atlanta, GA, USA Department of Biomedical Engineering, Northwestern University, Evanston, IL, USA Department of Cardiology, Northwestern University, Chicago, IL, USA Department of Preventive Medicine, Northwestern University, Chicago, IL, USA

AI总结 ProDM通过属性感知渐进校正扩散模型,有效校正非门控胸部CT中的运动伪影,提升冠状动脉钙评分的准确性与临床实用性。

Comments 21 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.03154 2026-01-01 cs.LG cs.AI cs.SE

SoundnessBench: A Soundness Benchmark for Neural Network Verifiers

SoundnessBench: 一种用于神经网络验证器的声学基准

Xingjian Zhou, Keyi Shen, Andy Xu, Hongji Xu, Cho-Jui Hsieh, Huan Zhang, Zhouxing Shi

机构 * University of California, Los Angeles(加州大学洛杉矶分校) Georgia Institute of Technology(佐治亚理工学院) Duke University(杜克大学) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) University of California, Riverside(加州大学河滨分校)

AI总结 SoundnessBench通过构建包含隐藏反例的基准,用于评估神经网络验证器的正确性。

Comments TMLR (December 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.17126 2026-01-01 cs.CV cs.LG

MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs

MM-SpuBench:迈向更好地理解多模态大语言模型中伪偏差的深入研究

Wenqian Ye, Bohan Liu, Guangtao Zheng, Di Wang, Yunsheng Ma, Xu Cao, Bolin Lai, James M. Rehg, Aidong Zhang

机构 * University of Virginia(弗吉尼亚大学) Purdue University(普渡大学) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Georgia Institute of Technology(佐治亚理工学院)

AI总结 MM-SpuBench通过分析多模态大语言模型中的伪偏差,揭示其存在与缓解的挑战,提供公开基准以促进相关技术发展。

Comments Accepted at KDD 2026 (Dataset and Benchmark Track)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.09132 2026-01-01 cs.LG

Jacobian-Enhanced Neural Networks

雅可比增强神经网络

Steven H. Berguin

机构 * Georgia Tech Research Institute(佐治亚理工学院研究机构)

AI总结 雅可比增强神经网络通过提高偏导数预测精度,在基于代理的优化中实现更高效的模型替代

Comments 34 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.23870 2026-01-01 cs.LG

Max-Entropy Reinforcement Learning with Flow Matching and A Case Study on LQR

最大熵强化学习与流匹配及LQR问题的案例研究

Yuyang Zhang, Yang Hu, Bo Dai, Na Li

机构 * School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院) Harvard University(哈佛大学) College of Computing, Georgia Institute of Technology(佐治亚理工学院计算机学院)

AI总结 本文提出了一种基于流模型的SAC变体,通过重要性采样流匹配技术提升策略更新效率,并在LQR问题中验证了其学习最优动作分布的能力。

详情

展开后加载摘要…

URL PDF HTML 收藏