大模型对齐与安全

Progressive Depth Up-scaling via Optimal Transport

Mingzi Cao, Xi Wang, Nikolaos Aletras

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL

Autonomous Navigation of Cloud-Controlled Quadcopters in Confined Spaces Using Multi-Modal Perception and LLM-Driven High Semantic Reasoning

Shoaib Ahmmad, Zubayer Ahmed Aditto, Md Mehrab Hossain, Noushin Yeasmin, Shorower Hossain

机构 * Department of Mechanical Engineering（机械工程系） ； Rajshahi University of Engineering and Technology（拉贾沙希工程与技术大学） ； Department of Industrial and Production Engineering（工业与生产工程系） ； Shahjalal University of Science and Technology（沙赫jalal科学与技术大学） ； Bangladesh University of Engineering and Technology（孟加拉工程与技术大学） ； Department of Urban and Regional Planning（城市与区域规划系） ； Department of Computer Science Engineering（计算机科学与工程系） ； United International University（联合国际大学） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Steering AI-Driven Personalization of Scientific Text for General Audiences

Taewook Kim, Dhruv Agarwal, Jordan Ackerman, Manaswi Saha

机构 * Northwestern University（西北大学） ； Cornell University（康奈尔大学） ； Center for Advanced AI, Accenture（Accenture高级人工智能中心） ； Accenture Labs（Accenture实验室） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

Comments 28 pages, 7 figures, 1 table. Accepted to PACM HCI (CSCW 2025)

Fed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuning

Xingke Yang, Liang Li, Sicong Li, Liwei Guan, Hao Wang, Xiaoqi Qi, Jiang Liu, Xin Fu, Miao Pan

专题命中 其他安全 ：alignment(abstract)；分类 cs.LG

The Escalator Problem: Identifying Implicit Motion Blindness in AI for Accessibility

Xiantao Zhang

机构 * Beihang University（北航大学） 纠错

专题命中 其他安全 ：safety(abstract)

Comments 9 pages, 3 figures, 2 tables. Accepted at CV4A11y, ICCV 2025

Multi-agent systems for chemical engineering: A review and perspective

Sophia Rupprecht, Qinghe Gao, Tanuj Karia, Artur M. Schweidtmann

专题命中 其他安全 ：safety(abstract)

Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning

Bao Li, Xiaomei Zhang, Miao Xu, Zhaoxin Fan, Xiangyu Zhu, Zhen Lei

机构 * CASIA（中国科学院自动化研究所） ； UCAS（中国科学院大学） ； CAIR, HKISI, CAS（中国科学院自动化研究所） ； Beihang University（北京航空航天大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Fusion-Based Brain Tumor Classification Using Deep Learning and Explainable AI, and Rule-Based Reasoning

Melika Filvantorkaman, Mohsen Piri, Maral Filvan Torkaman, Ashkan Zabihi, Hamidreza Moradi

专题命中 其他安全 ：alignment(abstract)

Comments 37 pages, 6 figures

Hybrid Machine Learning Framework for Predicting Geometric Deviations from 3D Surface Metrology

Hamidreza Samadi, Md Manjurul Ahsan, Shivakumar Raman

机构 * Industrial and Systems Engineering University of Oklahoma（工业与系统工程大学俄克拉荷马州立大学） 纠错

专题命中 其他安全 ：alignment(abstract)

DanceChat: Large Language Model-Guided Music-to-Dance Generation

Qing Wang, Xiaohang Yang, Yilan Dong, Naveen Raj Govindaraj, Gregory Slabaugh, Shanxin Yuan

专题命中 其他安全 ：alignment(abstract)

Constrained Hamiltonian Systems on Observation-Induced Fiber Bundles: Theory of Symmetry and Integrability

Dongzhe Zheng

专题命中 其他安全 ：safety(abstract)

Comments This paper establishes the complete mathematical theory underlying the practical framework presented in "Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures" (ICML 2025 (Forty-Second International Conference on Machine Learning) Spotlight, top 2.5% of ~12,000 submissions)

Exploring the Temporal Dynamics of Facial Mimicry in Emotion Processing Using Action Units

Meisam Jamshidi Seikavandi, Jostein Fimland, Maria Jung Barrett, Paolo Burelli

专题命中 其他安全 ：alignment(abstract)

Integrating Rules and Semantics for LLM-Based C-to-Rust Translation

Feng Luo, Kexing Ji, Cuiyun Gao, Shuzheng Gao, Jia Feng, Kui Liu, Xin Xia, Michael R. Lyu

专题命中 其他安全 ：safety(abstract)

Comments Accepted in ICSME 25 Industry Track

AdjustAR: AI-Driven In-Situ Adjustment of Site-Specific Augmented Reality Content

Nels Numan, Jessica Van Brummelen, Ziwen Lu, Anthony Steed

专题命中 其他安全 ：alignment(abstract)

Comments 4 pages, 1 figure, ACM UIST 2025 Poster

Large Language Models Facilitate Vision Reflection in Image Classification

Guoyuan An, JaeYoon Kim, SungEui Yoon

专题命中 其他安全 ：alignment(abstract)

Frontend Diffusion: Empowering Self-Representation of Junior Researchers and Designers Through Multi-agent System

Zijian Ding, Qinshi Zhang, Mohan Chi, Ziyi Wang

专题命中 其他安全 ：alignment(abstract)

Interleaved Speech-Text Language Models for Simple Streaming Text-to-Speech Synthesis

Yifan Yang, Shujie Liu, Jinyu Li, Hui Wang, Lingwei Meng, Haiyang Sun, Yuzhe Liang, Ziyang Ma, Yuxuan Hu, Rui Zhao, Jianwei Yu, Yan Lu, Xie Chen

专题命中 其他安全 ：alignment(abstract)