New York University（纽约大学） - arXivDaily 高校专区

2510.00537 2025-10-02 cs.LG cs.IT math.IT

Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?

Nandan Kumar Jha, Brandon Reagen

机构 * New York University（纽约大学）

Comments EMNLP 2025 Main Conference (Long paper)

2510.00329 2025-10-02 cs.RO

Learning Human Reaching Optimality Principles from Minimal Observation Inverse Reinforcement Learning

Sarmad Mehrdad, Maxime Sabbah, Vincent Bonnet, Ludovic Righetti

机构 * Machines in Motion Laboratory, New York University, USA（纽约大学运动机器实验室）； LAAS-CNRS, Université Paul Sabatier, CNRS, Toulouse, France（法国保罗·萨巴蒂埃大学LAAS-CNRS）； Image and Pervasive Access Laboratory (IPAL), CNRS-UMI, 2955, Singapore（新加坡图像与普及访问实验室（IPAL））； Artificial and Natural Intelligence Toulouse Institute (ANITI), Toulouse（图卢兹人工智能与自然智能研究所（ANITI））

Comments 8 pages, 4 figures

2510.00324 2025-10-02 cs.SE cs.IR cs.LG

Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?

Lucas Roberts, Denisa Roberts

机构 * Independent Researcher（独立研究者）； New York University（纽约大学）

Comments Accepted as a full paper at SIGIR-AP 2025

2510.00313 2025-10-02 eess.AS cs.SD

Post-Training Quantization for Audio Diffusion Transformers

Tanmay Khandelwal, Magdalena Fuentes

机构 * Courant Institute of Mathematical Sciences, New York University, NY, USA（Courant数学科学研究所，纽约大学）； MARL, New York University, NY, USA（MARL，纽约大学）； IDM, New York University, NY, USA（IDM，纽约大学）

Comments 5 pages, 4 figures, accepted at IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2025

2410.17661 2025-10-02 cs.AI cs.LG

PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context

Maximilian Augustin, Syed Shakib Sarwar, Mostafa Elhoushi, Sai Qian Zhang, Yuecheng Li, Barbara De Salvo

机构 * Tübingen AI Center University of Tübingen（图宾根人工智能中心图宾根大学）； Meta Inc.（Meta公司）； New York University（纽约大学）

Comments Published in CVPRW 2025

2402.12715 2025-10-02 cs.LG

The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning

Wenqian Ye, Luyang Jiang, Eric Xie, Guangtao Zheng, Yunsheng Ma, Xu Cao, Dongliang Guo, Daiqing Qi, Zeyu He, Yijun Tian, Megan Coffee, Zhe Zeng, Sheng Li, Ting-hao, Huang, Ziran Wang, James M. Rehg, Henry Kautz, 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）； Pennsylvania State University（宾夕法尼亚州立大学）； Amazon（亚马逊）； New York University（纽约大学）

Comments Version 3 with Major Revision; Github Link: https://github.com/wenqian-ye/Awesome-Spurious-Correlations