arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Korea Advanced Institute of Science and Technology(韩国科学技术院)

2026-08-31 至 2026-08-31 共收录 5
2608.08273 2026-08-31 cs.RO cs.CV 版本更新

Action- and Language-Conditioned Video Assessment for Embodied Control

面向具身控制的动作与语言条件视频评估

Hwanhee Kim, Jaehyun Jang, Seungmin Cha, Hyeonseo Yun, Donghoon Lee, Chang D. Yoo

机构 * Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院) School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院电气工程学院)

AI总结 该研究提出ALVA轨迹评估器,结合视觉观测、动作序列与语言指令评估具身控制任务,在模拟3D家庭环境中误报率低,作为反馈机制可提升闭环策略优化效果。

Comments 21 pages, 7 figures. v2: updated Funding section

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.02009 2026-08-31 cs.AI 版本更新

HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents

HALT:面向检索增强搜索智能体的感知验证式停止策略

Daeyoung Roh, Donghee Han

机构 * KAIST(韩国科学技术院)

AI总结 该研究针对检索增强搜索智能体的冗余检索问题,提出轻量级感知验证停止策略HALT,在三个多跳QA基准上减少冗余搜索且保持精确匹配,无需修改宿主智能体。

Comments Accepted to Findings of EMNLP 2026. 23 pages, 6 figures. Code: this https URL (https://github.com/Noverse0/HALT)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.19151 2026-08-31 cs.AI cs.MA 版本更新

Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning

TS-Debate:多模态协作辩论用于零样本时间序列推理

Patara Trirat, Jin Myung Kwak, Jay Heo, Heejun Lee, Sung Ju Hwang

机构 * KAIST Seoul(韩国科学技术院)

AI总结 TS-Debate通过多模态协作辩论框架,在零样本时间序列推理中实现显著性能提升,通过专门代理和结构化协议提升模态保真度和数值精度。

Comments EMNLP 2026 (Main), Project Page: this https URL (https://deepauto-ai.github.io/ts-debate/)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.00046 2026-08-31 eess.IV cs.CV cs.LG 版本更新

Mixture of Multicenter Experts in Multimodal AI for Debiased Radiotherapy Target Delineation

用于去偏放疗靶区勾画的多模态AI中的多中心专家混合模型

Yujin Oh, Sangjoon Park, Xiang Li, Pengfei Jin, Yi Wang, Jonathan Paly, Jason Efstathiou, Annie Chan, Jun Won Kim, Hwa Kyung Byun, Ik Jae Lee, Jaeho Cho, Chan Woo Wee, Peng Shu, Peilong Wang, Caiwen Jiang, Nathan Yu, Jason Holmes, Jong Chul Ye, Quanzheng Li, Wei Liu, Woong Sub Koom, Jin Sung Kim, Kyungsang Kim

机构 * Center for Advanced Medical Computing and Analysis (CAMCA), Department of Radiology, Massachusetts General Hospital (MGH) and Harvard Medical School(先进医学计算与分析中心(CAMCA)、放射科、麻省总医院(MGH)和哈佛医学院) Department of Radiation Oncology, Yonsei University College of Medicine(燕京大学医学院放射肿瘤科) Institute for Innovation in Digital Healthcare, Yonsei University(数字医疗创新研究所、燕京大学) Department of Radiation Oncology, Massachusetts General Hospital(麻省总医院放射肿瘤科) Department of Radiation Oncology, Gangnam Severance Hospital(江南松云医院放射肿瘤科) Department of Radiation Oncology, Yongin Severance Hospital(永兴松云医院放射肿瘤科) School of Computing, University of Georgia(佐治亚大学计算机学院) Department of Radiation Oncology, Mayo Clinic(梅奥诊所放射肿瘤科) Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology(金 Jaechul人工智能研究生院、韩国科学技术院)

AI总结 针对医疗AI的偏差问题,提出无需跨机构数据共享的多中心专家混合(MoME)框架,结合各中心少样本数据训练的前列腺癌放疗靶区勾画模型,在中心差异大或数据有限场景下优于基线,可定制且适配资源受限环境。

Comments In Revission

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.05098 2026-08-31 cs.LG stat.ML 版本更新

Improved off-policy training of diffusion samplers

扩散采样器的改进离策略训练

Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Esmeralda S. Whitammer

机构 * Mila, Université de Montréal(米拉-蒙特利尔大学) Jagiellonian University(雅盖隆大学) KAIST(韩国科学技术院) Ciela Institute(塞拉研究所) Dreamfold(德里姆福尔德公司) CIFAR(加拿大高级研究院) University of Edinburgh(爱丁堡大学)

AI总结 该研究针对扩散模型的离策略训练问题,提出结合重放缓冲区的目标空间局部搜索探索策略,提升了样本质量,同时阐明了现有算法的相对优势并质疑了过往部分结论,相关代码已公开。

Comments NeurIPS 2024; code: this https URL (https://github.com/GFNOrg/gfn-diffusion)

详情

展开后加载摘要…

URL PDF HTML 收藏