arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Carnegie Mellon University(卡内基梅隆大学)

2025-11-27 至 2025-11-27 共收录 9
2511.21584 2025-11-27 cs.RO cs.AI

Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving

基于模型的策略适应用于闭环端到端自动驾驶

Haohong Lin, Yunzhi Zhang, Wenhao Ding, Jiajun Wu, Ding Zhao

机构 * CMU(卡内基梅隆大学) Stanford(斯坦福大学) NVIDIA(英伟达)

AI总结 本文提出基于模型的策略适应框架,通过生成反事实轨迹和训练Q值模型提升自动驾驶在闭环环境中的鲁棒性和安全性。

Comments Published at NeurIPS 2025: https://openreview.net/forum?id=4OLbpaTKJe

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.21581 2025-11-27 cs.LG

Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning

学习何时停止:通过强化学习实现自适应潜在推理

Alex Ning, Yen-Ling Kuo, Gabe Gomes

机构 * University of Virginia(弗吉尼亚大学) Carnegie Mellon University(卡内基梅隆大学)

AI总结 本文提出通过强化学习优化潜在推理长度,实现更高效的推理压缩,实验显示推理长度减少52%且准确性无损失。

Comments 13 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.21045 2025-11-27 cs.SD

CartoonSing: Unifying Human and Nonhuman Timbres in Singing Generation

CartoonSing: 统一人类与非人类声音在歌唱生成中的表现

Jionghao Han, Jiatong Shi, Zhuoyan Tao, Yuxun Tang, Yiwen Zhao, Gus Xia, Shinji Watanabe

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Southern California(南加州大学) Renmin University of China(中国人民大学) Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

AI总结 CartoonSing通过统一框架生成非人类声音,解决非人类声音数据稀缺和音色差异问题,拓展了歌唱生成的应用范围。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14264 2025-11-27 cs.CV

Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models

Directed-Tokens: 一种稳健的多模态对齐方法用于大语言-视觉模型

Thanh-Dat Truong, Huu-Thien Tran, Tran Thai Son, Bhiksha Raj, Khoa Luu

机构 * CVIU Lab, University of Arkansas, USA(美国亚拉巴马大学CVIU实验室) Vietnam National University, Ho Chi Minh City University of Science, Vietnam(越南国家大学胡志明市科技大学) Carnegie Mellon University, USA(美国卡内基梅隆大学)

AI总结 本文提出Directed-Tokens方法,通过引入图像和文本顺序重建任务及新的损失函数,提升大语言-视觉模型的鲁棒性和跨模态对齐能力,在多个基准上取得最佳性能。

Comments Accepted to NeurIPS'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14652 2025-11-27 cs.CY cs.AI cs.LG

Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor

AI中的严谨性:进行严谨的AI工作需要一种更广泛、负责任的AI导向的严谨性观念

Alexandra Olteanu, Su Lin Blodgett, Agathe Balayn, Angelina Wang, Fernando Diaz, Flavio du Pin Calmon, Margaret Mitchell, Michael Ekstrand, Reuben Binns, Solon Barocas

机构 * Microsoft Research(微软研究院) Cornell Tech(康奈尔科技学院) Carnegie Mellon University(卡内基梅隆大学) Harvard University(哈佛大学) Hugging Face(Hugging Face公司) Drexel University(德雷塞尔大学) University of Oxford(牛津大学)

AI总结 本文提出AI研究需更广泛的严谨性观念,涵盖方法论、背景知识、规范标准、理论构念、报告方式及推论支持等方面,以提升AI工作的责任性和严谨性。

Comments 21 pages, 1 figure, 1 table, accepted at NeurIPS'25 position papers track

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18513 2025-11-27 cs.LG

Enhancing Training Data Attribution with Representational Optimization

通过表征优化增强训练数据归因

Weiwei Sun, Haokun Liu, Nikhil Kandpal, Colin Raffel, Yiming Yang

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Toronto(多伦多大学) Vector Institute(向量研究所)

AI总结 AirRep通过优化表征提升训练数据归因效率,实现与先进梯度方法相当的性能,且推理效率提高近两数量级。

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15277 2025-11-27 cs.CL

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Web-Shepherd: 促进强化网络代理的PRMs

Hyungjoo Chae, Sunghwan Kim, Junhee Cho, Seungone Kim, Seungjun Moon, Gyeom Hwangbo, Dongha Lim, Minjin Kim, Yeonjun Hwang, Minju Gwak, Dongwook Choi, Minseok Kang, Gwanhoon Im, ByeongUng Cho, Hyojun Kim, Jun Hee Han, Taeyoon Kwon, Minju Kim, Beong-woo Kwak, Dongjin Kang, Jinyoung Yeo

机构 * Georgia Institute of Technology(佐治亚理工学院) Department of Artificial Intelligence, Yonsei University(延世大学人工智能系) Carnegie Mellon University(卡内基梅隆大学)

AI总结 Web-Shepherd是首个用于强化网络代理的PRM,通过构建大规模数据集和元评估基准,提升了网络导航任务的准确性和效率。

Comments NeurIPS 2025 Spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.08135 2025-11-27 cs.SE cs.AI cs.DC cs.PF

Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions

利用AI实现高效且可信的HPC软件:挑战与研究方向

Keita Teranishi, Harshitha Menon, William F. Godoy, Prasanna Balaprakash, David Bau, Tal Ben-Nun, Abhinav Bhatele, Franz Franchetti, Michael Franusich, Todd Gamblin, Giorgis Georgakoudis, Tom Goldstein, Arjun Guha, Steven Hahn, Costin Iancu, Zheming Jin, Terry Jones, Tze Meng Low, Het Mankad, Narasinga Rao Miniskar, Mohammad Alaul Haque Monil, Daniel Nichols, Konstantinos Parasyris, Swaroop Pophale, Pedro Valero-Lara, Jeffrey S. Vetter, Samuel Williams, Aaron Young

机构 * Oak Ridge National Laboratory(奥克荷厄斯国家实验室) Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室) Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室) Carnegie Mellon University(卡内基梅隆大学) Northeastern University(东北大学) University of Maryland(马里兰大学) SpiralGen Inc.(SpiralGen公司)

AI总结 本文探讨了利用AI改进HPC软件的挑战与研究方向,提出通过Ellora和Durban项目推动AI在HPC软件发展中的应用。

Comments 12 pages, 1 Figure, Accepted at "The 1st International Workshop on Foundational Large Language Models Advances for HPC" LLM4HPC to be held in conjunction with ISC High Performance 2025

Journal ref In: Neuwirth, S., Paul, A.K., Weinzierl, T., Carson, E.C. (eds) High Performance Computing. ISC High Performance 2025. Lecture Notes in Computer Science, vol 16091. Springer, Cham

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.09646 2025-11-27 cs.CV cs.RO

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

Hamba: 基于图引导双扫描Mamba的单视角3D手形重建

Haoye Dong, Aviral Chharia, Wenbo Gou, Francisco Vicente Carrasco, Fernando De la Torre

机构 * Carnegie Mellon University(卡内基梅隆大学)

AI总结 Hamba通过图引导双扫描Mamba框架,高效学习关节空间关系,实现更准确的3D手形重建。

Comments NeurIPS 2024; Project Website: https://humansensinglab.github.io/Hamba/

Journal ref NeurIPS, Vancouver, Canada, 2024, pp. 2127-2160

详情

展开后加载摘要…

URL PDF HTML 收藏