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)

共收录 2349
2502.12084 2025-07-03 cs.CL

VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues

Jianshu Zhang, Dongyu Yao, Renjie Pi, Paul Pu Liang, Yi R. Fung

机构 * Hong Kong University of Science and Technology(香港科技大学) Carnegie Mellon University(卡内基梅隆大学) Massachusetts Institute of Technology(麻省理工学院)

Comments Project Page: https://vlm2-bench.github.io/ Camera Ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.07762 2025-07-03 cs.LG

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

Zhiyuan Zhou, Andy Peng, Qiyang Li, Sergey Levine, Aviral Kumar

机构 * UC Berkeley(加州大学伯克利分校) Carnegie Mellon University(卡内基梅隆大学)

Journal ref International Conference on Learning Representation (ICLR) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00898 2025-07-02 cs.CV cs.CL

ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models

Zifu Wan, Ce Zhang, Silong Yong, Martin Q. Ma, Simon Stepputtis, Louis-Philippe Morency, Deva Ramanan, Katia Sycara, Yaqi Xie

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

Comments Accepted by ICCV 2025. Project page: https://zifuwan.github.io/ONLY/

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00509 2025-07-02 cs.CL cs.AI

TeamCMU at Touché: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search

To Eun Kim, João Coelho, Gbemileke Onilude, Jai Singh

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23874 2025-07-01 eess.AS cs.SD

URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement Competition

Jiahe Wang, Chenda Li, Wei Wang, Wangyou Zhang, Samuele Cornell, Marvin Sach, Robin Scheibler, Kohei Saijo, Yihui Fu, Zhaoheng Ni, Anurag Kumar, Tim Fingscheidt, Shinji Watanabe, Yanmin Qian

机构 * Shanghai Jiao Tong University(上海交通大学) Carnegie Mellon University(卡内基梅隆大学) Technische Universität Braunschweig(Braunschweig 技术大学) Google DeepMind(谷歌DeepMind) Waseda University(早稻田大学) Meta

Comments Submitted to ASRU2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23456 2025-07-01 math.ST cs.DS cs.LG stat.ML stat.TH

Sampling and Identity-Testing Without Approximate Tensorization of Entropy

William Gay, William He, Nicholas Kocurek, Ryan O'Donnell

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23072 2025-07-01 cs.CV

Unsupervised 3D Braided Hair Reconstruction from a Single-View Image

Jing Gao

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

Comments 6 pages, 3 figures, accepted to the 2025 International Conference on Machine Vision Applications (MVA 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23049 2025-07-01 cs.AI cs.CL cs.SD eess.AS

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks

Leander Melroy Maben, Gayathri Ganesh Lakshmy, Srijith Radhakrishnan, Siddhant Arora, Shinji Watanabe

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19107 2025-07-01 cs.HC cs.AI

Improving Student-AI Interaction Through Pedagogical Prompting: An Example in Computer Science Education

Ruiwei Xiao, Xinying Hou, Runlong Ye, Majeed Kazemitabaar, Nicholas Diana, Michael Liut, John Stamper

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Michigan(密歇根大学) University of Toronto(多伦多大学) Colgate University(科尔盖特大学) University of Toronto Mississauga(多伦多大学密西根分校)

Comments Under review for Elsevier Journal. Journal policy allows submitting as preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12576 2025-07-01 cs.CL cs.AI

Enabling Precise Topic Alignment in Large Language Models Via Sparse Autoencoders

Ananya Joshi, Celia Cintas, Skyler Speakman

机构 * Carnegie Mellon University(卡内基梅隆大学) IBM Research(IBM研究院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.04205 2025-07-01 cs.CL

A Context-aware Framework for Translation-mediated Conversations

José Pombal, Sweta Agrawal, Patrick Fernandes, Emmanouil Zaranis, André F. T. Martins

机构 * Unbabel Instituto de Telecomunicações(电信研究所) Instituto Superior Técnico, Universidade de Lisboa(里斯本大学技术研究所) Carnegie Mellon University(卡内基梅隆大学) ELLIS Unit Lisbon(里斯本ELLIS单位)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.08870 2025-07-01 cs.CL cs.AI cs.LG

The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models

Daniel P. Jeong, Pranav Mani, Saurabh Garg, Zachary C. Lipton, Michael Oberst

机构 * Carnegie Mellon University(卡内基梅隆大学) Abridge Mistral AI Johns Hopkins University(约翰霍普金斯大学)

Comments Extended version of EMNLP 2024 paper arXiv:2411.04118. Includes additional results on clinical note QA tasks and supervised fine-tuning evaluations

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.06832 2025-07-01 cs.CV

FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving

Yutao Zhu, Xiaosong Jia, Xinyu Yang, Junchi Yan

机构 * School of Computer Science and School of Artificial Intelligence, Shanghai Jiao Tong University(计算机科学学院和人工智能学院,上海交通大学) Carnegie Mellon University(卡内基梅隆大学)

Comments Accepted by ICRA 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.11594 2025-07-01 cs.LG cs.AI

Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning

Taejin Kim, Jiarui Li, Shubhranshu Singh, Nikhil Madaan, Carlee Joe-Wong

机构 * University of Michigan, Michigan, USA(密歇根大学) Carnegie Mellon University, Pittsburgh, Pennsylvania, USA(卡内基梅隆大学)

Comments 15 pages, 8 main pages of text, 13 figures, 5 tables. Made for a Neurips workshop on backdoor attacks - extended version

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22492 2025-07-01 cs.CY cs.AI

Report on NSF Workshop on Science of Safe AI

Rajeev Alur, Greg Durrett, Hadas Kress-Gazit, Corina Păsăreanu, René Vidal

机构 * University of Pennsylvania(宾夕法尼亚大学) NASA Ames and CMU(NASA阿姆斯特朗研究中心和卡内基梅隆大学) The University of Texas at Austin(德克萨斯大学奥斯汀分校) Cornell University(康奈尔大学) Penn(宾夕法尼亚大学) UT Austin(德克萨斯大学奥斯汀分校) CMU(卡内基梅隆大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22401 2025-06-30 cs.LG math.OC

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

Tong Yang, Bo Dai, Lin Xiao, Yuejie Chi

机构 * CMU Carnegie Mellon University(卡内基梅隆大学) Georgia Institute of Technology(佐治亚理工学院) Meta Fundamental AI Research, Meta(Meta基础人工智能研究) CMU(卡内基梅隆大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22660 2025-06-30 cs.LG cs.AI

Maximizing Confidence Alone Improves Reasoning

Mihir Prabhudesai, Lili Chen, Alex Ippoliti, Katerina Fragkiadaki, Hao Liu, Deepak Pathak

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

Comments Website: https://rent-rl.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.07596 2025-06-30 cs.LG stat.ME stat.ML

Learning treatment effects while treating those in need

Bryan Wilder, Pim Welle

机构 * Carnegie Mellon University(卡内基梅隆大学) Allegheny County Department of Human Services(阿利根尼县人类服务部)

Journal ref ACM EC 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.20969 2025-06-27 cs.RO cs.CV

ThermalDiffusion: Visual-to-Thermal Image-to-Image Translation for Autonomous Navigation

Shruti Bansal, Wenshan Wang, Yifei Liu, Parv Maheshwari

机构 * Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所)

Comments Accepted at Thermal Infrared in Robotics (TIRO) Workshop, ICRA 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.20609 2025-06-26 cs.SD cs.AI cs.MM eess.AS

Deciphering GunType Hierarchy through Acoustic Analysis of Gunshot Recordings

Ankit Shah, Rita Singh, Bhiksha Raj, Alexander Hauptmann

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

Comments 4 pages + 1 References

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.20155 2025-06-26 cs.CV

Towards Efficient Exemplar Based Image Editing with Multimodal VLMs

Avadhoot Jadhav, Ashutosh Srivastava, Abhinav Java, Silky Singh, Tarun Ram Menta, Surgan Jandial, Balaji Krishnamurthy

机构 * Indian Institute of Technology, Bombay(印度理工学院班加罗尔分校) Indian Institute of Technology, Roorkee(印度理工学院罗尔基分校) Microsoft Research(微软研究院) Stanford University(斯坦福大学) Adobe MDSR(Adobe MDSR实验室) Carnegie Mellon University(卡内基梅隆大学)

Comments Accepted at ECCV 2024 (AI4VA Workshop)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.20128 2025-06-26 cs.CL cs.AI cs.LG

CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation

Aashiq Muhamed

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

Comments Accepted at LLM4Eval @ SIGIR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17289 2025-06-26 cs.AI cs.LG

Evaluating Generalization and Representation Stability in Small LMs via Prompting, Fine-Tuning and Out-of-Distribution Prompts

Rahul Raja, Arpita Vats

机构 * Boston University, Boston, USA(波士顿大学) Carnegie Mellon University, Pittsburgh, USA(卡内基梅隆大学) Stanford University, Palo Alto, USA(斯坦福大学)

Comments Accepted at ICML

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.17852 2025-06-26 cs.LG stat.ML

Counterfactual Fairness through Transforming Data Orthogonal to Bias

Shuyi Chen, Shixiang Zhu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.01259 2025-06-26 cs.LG cs.AI

Do Concept Bottleneck Models Respect Localities?

Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo, Mateja Jamnik

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Cambridge(剑桥大学)

Comments Published at TMLR

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19724 2025-06-25 cs.AI

From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking

Gyeongwon James Kim, Alex Wilf, Louis-Philippe Morency, Daniel Fried

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19578 2025-06-25 cs.DC cs.AI

Towards an Introspective Dynamic Model of Globally Distributed Computing Infrastructures

Ozgur O. Kilic, David K. Park, Yihui Ren, Tatiana Korchuganova, Sairam Sri Vatsavai, Joseph Boudreau, Tasnuva Chowdhury, Shengyu Feng, Raees Khan, Jaehyung Kim, Scott Klasky, Tadashi Maeno, Paul Nilsson, Verena Ingrid Martinez Outschoorn, Norbert Podhorszki, Frédéric Suter, Wei Yang, Yiming Yang, Shinjae Yoo, Alexei Klimentov, Adolfy Hoisie

机构 * Brookhaven National Laboratory(布鲁赫斯国家实验室) Oak Ridge National Laboratory(橡树岭国家实验室) University of Pittsburgh(匹兹堡大学) Carnegie Mellon University(卡内基梅隆大学) University of Massachusetts(马萨诸塞大学) SLAC National Accelerator Laboratory(SLAC国家加速器实验室)

Journal ref CHEP 2024, EPJ Web of Conferences (EPJ WoC)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19396 2025-06-25 cs.LG

Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators

Shanda Li, Shinjae Yoo, Yiming Yang

机构 * Carnegie Mellon University(卡内基梅隆大学) Brookhaven National Laboratory(布鲁克海文国家实验室)

Comments ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19291 2025-06-25 cs.CV

HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis

Xiaoyuan Wang, Yizhou Zhao, Botao Ye, Xiaojun Shan, Weijie Lyu, Lu Qi, Kelvin C. K. Chan, Yinxiao Li, Ming-Hsuan Yang

机构 * CMU(卡内基梅隆大学) ETH Zurich(苏黎世联邦理工学院) UC San Diego(圣地亚哥大学) UC Merced(默塞德大学) Insta360(Insta360公司) Google DeepMind(谷歌DeepMind)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19025 2025-06-25 math.ST cs.AI cs.LG stat.ME stat.ML stat.TH

Statistical Inference for Optimal Transport Maps: Recent Advances and Perspectives

Sivaraman Balakrishnan, Tudor Manole, Larry Wasserman

机构 * Department of Statistics and Data Science(统计与数据科学系) Machine Learning Department(机器学习系) Carnegie Mellon University(卡内基梅隆大学) Statistics and Data Science Center(统计与数据科学中心) Massachusetts Institute of Technology(麻省理工学院)

Comments 36 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏