语言大模型 / LLM

MindEye-OmniAssist: A Gaze-Driven LLM-Enhanced Assistive Robot System for Implicit Intention Recognition and Task Execution

Zejia Zhang, Bo Yang, Xinxing Chen, Weizhuang Shi, Haoyuan Wang, Wei Luo, Jian Huang

机构 * Hubei Key Laboratory of Brain-Inspired Intelligent Systems, Huazhong University of Science and Technology（脑启发智能系统湖北省重点实验室，华中科技大学） ； Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（图像处理与智能控制教育部重点实验室，人工智能与自动化学院，华中科技大学） ； state key laboratory of intelligent vehicle safety technology, chongqing changan automobile co ltd（智能车辆安全技术 state key laboratory，重庆长安汽车有限公司） ； Science and technology innovation center, China ship development and design centre（科技创新中心，中国船舶工业设计研究中心） 纠错

专题命中 其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation

Jingquan Wang, Andrew Negrut, Harry Zhang, Khailanii Slaton, Shu Wang, Radu Serban, Jinlong Wu, Dan Negrut

机构 * Department of Mechanical Engineering, University of Wisconsin-Madison（威斯康星大学麦迪逊分校机械工程系） ； Department of Computer Science, Rice University（里德大学计算机科学系） 纠错

专题命中 其他LLM ：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.AI

Prompt Orchestration Markup Language

Yuge Zhang, Nan Chen, Jiahang Xu, Yuqing Yang

机构 * Microsoft Research（微软研究院） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments All findings in this paper are derived from a POML snapshot as of February 2025

Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder

Jingchao Wang, Zhijian Wu, Dingjiang Huang, Yefeng Zheng, Hong Wang

专题命中 其他LLM ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 9 pages, 4 figures

AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs

Yi-Ting Shen, Sungmin Eum, Doheon Lee, Rohit Shete, Chiao-Yi Wang, Heesung Kwon, Shuvra S. Bhattacharyya

机构 * University of Maryland, College Park（马里兰大学学院市分校） ； DEVCOM Army Research Laboratory（陆军研究实验室） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments ICCV 2025

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points

Aditya Varre, Gizem Yüce, Nicolas Flammarion

机构 * Theory of Machine Learning Lab, EPFL, Switzerland（机器学习理论实验室，瑞士联邦理工学院） 纠错

专题命中 其他LLM ：language model(abstract)；分类 cs.LG

Comments ICML2025

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage

Krishna Kanth Nakka, Xue Jiang, Dmitrii Usynin, Xuebing Zhou

专题命中 其他LLM ：LLM(abstract)

Comments Preprint. V2 Updated with dataset filtering, benchmarking privacy evaluator and additional latent space visualizations

Evidence of Nonlinear Signatures in Solar Wind Proton Density at the L1 Lagrange point

Dario Javier Zamora, Facundo Abaca, Bruno Zossi, Ana Georgina Elias

专题命中 其他LLM ：prompting(abstract)

Journal ref A&A 700, A166 (2025)