Cornell University（康奈尔大学）

2510.22852 2025-10-28 cs.LG cs.AI

Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

Marianne Arriola, Yair Schiff, Hao Phung, Aaron Gokaslan, Volodymyr Kuleshov

机构 * Department of Computer Science, Cornell University（计算机科学系，康奈尔大学）

Comments NeurIPS 2025. We provide the code at https://github.com/kuleshov-group/e2d2

2504.17959 2025-10-28 cs.RO cs.LG cs.SY eess.SY

CIVIL: Causal and Intuitive Visual Imitation Learning

Yinlong Dai, Robert Ramirez Sanchez, Ryan Jeronimus, Shahabedin Sagheb, Cara M. Nunez, Heramb Nemlekar, Dylan P. Losey

机构 * Collaborative Robotics Lab, Mechanical Engineering Department, Virginia Tech（弗吉尼亚理工学院与州立大学机械工程系协作机器人实验室）； Mechanical Engineering Department, California State University, Northridge（加州州立大学北岭分校机械工程系）； Mechanical Engineering Department, Cornell University（康奈尔大学机械工程系）

2504.12989 2025-10-28 quant-ph cs.IT cs.LG math.IT math.ST stat.TH

Query Complexity of Classical and Quantum Channel Discrimination

Theshani Nuradha, Mark M. Wilde

机构 * School of Electrical ； Computer Engineering, Cornell University, Ithaca, New York 14850, USA ； Department of Mathematics \& Illinois Quantum Information Science ； Technology (IQUIST) Center, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA

Comments v3: 35 pages, published version; v2: 33 pages, Added tighter and precise characterization of sample and query complexity in Theorem 11 (for states), Theorem 12 (for general channels), and Corollaries 10 and 14 for classical-quantum channels; v1:22 pages; see also the independent work "Sampling complexity of quantum channel discrimination" DOI 10.1088/1572-9494/adcb9e

Journal ref Quantum Science and Technology, vol. 10, no. 4, page 045075, December 2025

2502.10999 2025-10-28 cs.CV cs.AI cs.CL cs.MM

ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations

Bowen Jiang, Yuan Yuan, Xinyi Bai, Zhuoqun Hao, Alyson Yin, Yaojie Hu, Wenyu Liao, Lyle Ungar, Camillo J. Taylor

机构 * University of Pennsylvania（宾夕法尼亚大学）； Cornell University（康奈尔大学）； University of California, Irvine（加州大学伊藤分校）

Comments The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings