arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

New York University(纽约大学)

共收录 1617
2509.07979 2025-10-13 cs.CV

Visual Representation Alignment for Multimodal Large Language Models

Heeji Yoon, Jaewoo Jung, Junwan Kim, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim

机构 * KAIST AI(韩国科学技术院人工智能研究所) New York University(纽约大学) Chung-Ang University(Chung-Ang 大学) Korea University(韩国大学) ETH Zürich(苏黎世联邦理工学院)

Comments Project Page: https://cvlab-kaist.github.io/VIRAL/

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22087 2025-10-13 cs.RO

An Introduction to Zero-Order Optimization Techniques for Robotics

Armand Jordana, Jianghan Zhang, Joseph Amigo, Ludovic Righetti

机构 * Machines in Motion Laboratory, New York University, USA(运动机器实验室,纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09014 2025-10-13 cs.CL

Learning to Reason Across Parallel Samples for LLM Reasoning

Jianing Qi, Xi Ye, Hao Tang, Zhigang Zhu, Eunsol Choi

机构 * CUNY Grad Center(纽约大学研究生中心) Princeton University(普林斯顿大学) BMCC(布鲁克林社区学院) CCNY(城市学院) New York University(纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08466 2025-10-10 cs.LG

In-Context Clustering with Large Language Models

Ying Wang, Mengye Ren, Andrew Gordon Wilson

机构 * New York University(纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08449 2025-10-10 cs.CV

Hierarchical Spatial Algorithms for High-Resolution Image Quantization and Feature Extraction

Noor Islam S. Mohammad

机构 * New York University, Department of Computer Science and Engineering(纽约大学计算机科学与工程系)

Comments There are 14 pages journal paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08372 2025-10-10 cs.CL cs.LG

On the Relationship Between the Choice of Representation and In-Context Learning

Ioana Marinescu, Kyunghyun Cho, Eric Karl Oermann

机构 * NYU(纽约大学)

Comments 25 pages, 6 figures, 10 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08365 2025-10-10 cs.CL

Two-Stage Voting for Robust and Efficient Suicide Risk Detection on Social Media

Yukai Song, Pengfei Zhou, César Escobar-Viera, Candice Biernesser, Wei Huang, Jingtong Hu

机构 * Department of Electrical and Computer Engineering(电气与计算机工程系) Department of Informatics and Networked Systems(信息与网络系统系) University of Pittsburgh(匹兹堡大学) Department of Psychiatry(精神病学系) Tandon School of Engineering(塔能工程学院) New York University(纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.16746 2025-10-10 cs.CV cs.CL cs.LG

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Ang Li, Charles Wang, Deqing Fu, Kaiyu Yue, Zikui Cai, Wang Bill Zhu, Ollie Liu, Peng Guo, Willie Neiswanger, Furong Huang, Tom Goldstein, Micah Goldblum

机构 * Columbia University(哥伦比亚大学) University of Maryland(马里兰大学) University of Southern California(南加州大学) New York University(纽约大学)

Comments dataset link: https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00885 2025-10-10 cs.CL cs.LG

Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check

Nicholas Lourie, Michael Y. Hu, Kyunghyun Cho

机构 * New York University(纽约大学) Prescient Design CIFAR LMB

Comments EMNLP Findings 2025 Camera Ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05130 2025-10-10 cs.CL

Submodular Context Partitioning and Compression for In-Context Learning

Shaoyi Zheng, Canyu Zhang, Tianyi Zhou, Shengjie Wang

机构 * New York University(纽约大学) University of Washington Seattle(华盛顿大学西雅图分校) University of Maryland College Park(马里兰大学学院市分校)

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.08797 2025-10-10 cs.LG cond-mat.dis-nn math.PR

Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden

机构 * Center for Cosmology and Particle Physics New York University(纽约大学宇宙与粒子物理中心) Courant Institute of Mathematical Sciences New York University(纽约大学数学科学学院)

Comments JMLR Version

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20757 2025-10-09 cs.CL

MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search

Yunhai Hu, Yilun Zhao, Chen Zhao, Arman Cohan

机构 * Yale University(耶鲁大学) New York University(纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17353 2025-10-09 cs.LG cs.AI

NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks

Alex Reneau, Jerry Yao-Chieh Hu, Zhongfang Zhuang, Ting-Chun Liu, Xiang He, Judah Goldfeder, Nadav Timor, Allen G Roush, Ravid Shwartz-Ziv

机构 * Ensemble AI Columbia University(哥伦比亚大学) Weizmann Institute of Science(魏茨曼科学研究所) Wand AI/Thoughtworks NYU(纽约大学)

Comments Code is available at https://github.com/ensemble-core/NdLinear

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.19732 2025-10-09 cs.CL

Speculative Decoding and Beyond: An In-Depth Survey of Techniques

Yunhai Hu, Zining Liu, Zhenyuan Dong, Tianfan Peng, Bradley McDanel, Sai Qian Zhang

机构 * New York University(纽约大学) University of Pennsylvania(宾夕法尼亚大学) Shenzhen Institute of Information Technology(深圳信息技术研究所) Franklin and Marshall College(弗兰克林与马歇尔学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06634 2025-10-09 cs.LG

Three Forms of Stochastic Injection for Improved Distribution-to-Distribution Generative Modeling

Shiye Su, Yuhui Zhang, Linqi Zhou, Rajesh Ranganath, Serena Yeung-Levy

机构 * Stanford University(斯坦福大学) Luma AI New York University(纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06475 2025-10-09 cs.AI cs.CL

PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles

Yitao Long, Yuru Jiang, Hongjun Liu, Yilun Zhao, Jingchen Sun, Yiqiu Shen, Chen Zhao, Arman Cohan, Dennis Shasha

机构 * New York University(纽约大学) Zhejiang University(浙江大学) Yale University(耶鲁大学) University at Buffalo, SUNY(布法罗大学) NYU Grossman School of Medicine(纽约大学医学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06426 2025-10-09 cs.CL

FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering

Yitao Long, Tiansheng Hu, Yilun Zhao, Arman Cohan, Chen Zhao

机构 * NYU Shanghai(纽约大学上海校区) Yale University(耶鲁大学) New York University(纽约大学)

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01861 2025-10-09 stat.AP cs.AI cs.LG

ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation

Junyi Mo, Jiayu Li, Duo Zhang, Elynn Chen

机构 * New York University(纽约大学)

Comments The 6th ACM International Conference on AI in Finance (ICAIF 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.00656 2025-10-09 cs.CL cs.LG

2 OLMo 2 Furious

Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, Allyson Ettinger, Michal Guerquin, David Heineman, Hamish Ivison, Pang Wei Koh, Jiacheng Liu, Saumya Malik, William Merrill, Lester James V. Miranda, Jacob Morrison, Tyler Murray, Crystal Nam, Jake Poznanski, Valentina Pyatkin, Aman Rangapur, Michael Schmitz, Sam Skjonsberg, David Wadden, Christopher Wilhelm, Michael Wilson, Luke Zettlemoyer, Ali Farhadi, Noah A. Smith, Hannaneh Hajishirzi

机构 * Allen Institute for AI(艾伦人工智能研究所) University of Washington(华盛顿大学) New York University(纽约大学)

Comments Shorter version accepted to COLM 2025. Updated to include 32B results. Model demo available at playground.allenai.org

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.09956 2025-10-09 cs.LG math.ST stat.TH

The Adversarial Consistency of Surrogate Risks for Binary Classification

Natalie Frank, Jonathan Niles-Weed

机构 * Courant Institute(Courant 院) New York University(纽约大学)

Comments 17 pages, published in NeurIps 2023. version 3: added acknowledgements, no other changes. version 2: reorganized Section 4 and added proofs of the approximate complimentary slackness theorems. arXiv admin note: text overlap with arXiv:2206.09099

Journal ref Advances in Neural Information Processing Systems 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.09098 2025-10-09 cs.LG math.ST stat.TH

Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification

Natalie S. Frank, Jonathan Niles-Weed

机构 * Courant Institute New York University(纽约大学Courant学院) Courant Institute and Center for Data Science New York University(纽约大学Courant学院和数据科学中心)

Comments 42 pages. version 2: corrects several errors and employs a significantly different proof technique. version 3: modifies the arXiv author list but has no other changes. version 4: improved exposition and fixed typos

Journal ref Journal of Machine Leanring Research 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05949 2025-10-08 cs.LG cs.AI cs.CV stat.ML

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density

Randall Balestriero, Nicolas Ballas, Mike Rabbat, Yann LeCun

机构 * Meta-FAIR Brown University(布朗大学) NYU(纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14252 2025-10-08 cs.CL cs.AI

LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures

Hai Huang, Yann LeCun, Randall Balestriero

机构 * Atlassian(Atlassian公司) NYU(纽约大学) Brown University(布朗大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05707 2025-10-08 cs.RO cs.LG math.OC

Stable Robot Motions on Manifolds: Learning Lyapunov-Constrained Neural Manifold ODEs

David Boetius, Abdelrahman Abdelnaby, Ashok Kumar, Stefan Leue, Abdalla Swikir, Fares J. Abu-Dakka

机构 * Department of Computer and Information Sciences University of Konstanz(计算机与信息科学系康斯坦茨大学) Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence(机器人学系Mohamed bin Zayed人工智能大学) Mechanical Engineering Department, New York University Abu Dhabi(机械工程系纽约大学阿布扎克分校)

Comments 12 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05558 2025-10-08 cs.CV cs.LG

Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics

Christopher Hoang, Mengye Ren

机构 * New York University(纽约大学)

Comments Project page: https://agenticlearning.ai/midway-network/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05446 2025-10-08 cs.LG stat.ML

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs

Runlin Zhou, Chixiang Chen, Elynn Chen

机构 * Department of Statistics, University of Science and Technology of China(统计系,中国科学技术大学) Department of Epidemiology and Public Health, University of Maryland, Baltimore(流行病学与公共卫生系,马里兰大学巴尔的摩分校) Department of Technology, Operations, and Statistics, Stern School of Business, New York University(技术、运营与统计系,纽约大学斯特恩商学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05205 2025-10-08 cs.LG astro-ph.CO

A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors

Sebastian Wagner-Carena, Aizhan Akhmetzhanova, Sydney Erickson

机构 * Center for Computational Astrophysics, Flatiron Institute(Flatiron Institute 计算天文中心) Center for Data Science, New York University(纽约大学数据科学中心) Department of Physics, Harvard University(哈佛大学物理系) Department of Physics, Stanford University(斯坦福大学物理系)

Comments Accepted to main conference of NeurIPS 2025. Code available at https://github.com/swagnercarena/ddprism

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05152 2025-10-08 cs.CL cs.AI

A Single Character can Make or Break Your LLM Evals

Jingtong Su, Jianyu Zhang, Karen Ullrich, Léon Bottou, Mark Ibrahim

机构 * FAIR at Meta(Meta 的 FAIR 研究院) New York University(纽约大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.19521 2025-10-08 cs.CL cs.LG

Intent-Aware Schema Generation And Refinement For Literature Review Tables

Vishakh Padmakumar, Joseph Chee Chang, Kyle Lo, Doug Downey, Aakanksha Naik

机构 * New York University(纽约大学) AI2 Northwestern University(西北大学)

Comments To Appear at EMNLP Findings 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09389 2025-10-08 cs.CL

Measuring LLM Novelty As The Frontier Of Original And High-Quality Output

Vishakh Padmakumar, Chen Yueh-Han, Jane Pan, Valerie Chen, He He

机构 * New York University(纽约大学) Carnegie Mellon University(卡内基梅隆大学)

Comments Updated results with higher coverage of open-data models and better quality judgments

详情

展开后加载摘要…

URL PDF HTML 收藏