大模型对齐与安全

Artificial intelligence and the Gulf Cooperation Council workforce adapting to the future of work

Mohammad Rashed Albous, Melodena Stephens, Odeh Rashed Al-Jayyousi

专题命中 AI治理与伦理 ：alignment(abstract)；分类 cs.AI、cs.CY

Journal ref Humanit Soc Sci Commun 12, 1649 (2025)

QOC DAO -- Stepwise Development Towards an AI Driven Decentralized Autonomous Organization

Marc Jansen, Christophe Verdot

专题命中 AI治理与伦理 ：trustworthy(abstract)；分类 cs.CY

3D Guard-Layer: An Integrated Agentic AI Safety System for Edge Artificial Intelligence

Eren Kurshan, Yuan Xie, Paul Franzon

专题命中 其他安全 ：safety(title,abstract)；AI safety(title,abstract)；分类 cs.AI

Comments Resubmitting Re: Arxiv Committee Approval

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

Zhongyang Li, Ziyue Li, Tianyi Zhou

机构 * Johns Hopkins University（约翰霍普金斯大学） ； University of Maryland, College Park（马里兰大学学院公园分校） 纠错

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

Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models

Jiwoo Shin, Byeonghu Na, Mina Kang, Wonhyeok Choi, Il-Chul Moon

机构 * KAIST（韩国科学技术院） 纠错

专题命中 其他安全 ：safety(title)；分类 cs.AI、cs.LG

Comments Accepted at NeurIPS 2025 Workshop on Generative and Protective AI for Content Creation

Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders

John F. Wu, Michael Walmsley

机构 * Space Telescope Science Institute（太空望远镜科学研究所） ； Johns Hopkins University（约翰霍普金斯大学） ； University of Toronto（多伦多大学） 纠错

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

Comments Authors contributed equally to this work. Accepted to NeurIPS Machine Learning and the Physical Sciences Workshop. See trained model at https://huggingface.co/mwalmsley/euclid-rr2-mae, HuggingFace demo at https://huggingface.co/spaces/mwalmsley/euclid_masked_autoencoder, and code at https://github.com/jwuphysics/euclid-galaxy-morphology-saes

The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?

Denis Sutter, Julian Minder, Thomas Hofmann, Tiago Pimentel

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

Comments NeurIPS 2025 (Spotlight)

Knowledge Graph Analysis of Legal Understanding and Violations in LLMs

Abha Jha, Abel Salinas, Fred Morstatter

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

No Cords Attached: Coordination-Free Concurrent Lock-Free Queues

Yusuf Motiwala

专题命中 其他安全 ：safety(abstract)

Comments 10 pages, 2 figures, 3 tables. Lock-free concurrent queue with coordination-free memory reclamation

Signaling in the Age of AI: Evidence from Cover Letters

Jingyi Cui, Gabriel Dias, Justin Ye

专题命中 其他安全 ：alignment(abstract)

Domain Adaptation from Generated Multi-Weather Images for Unsupervised Maritime Object Classification

Dan Song, Shumeng Huo, Wenhui Li, Lanjun Wang, Chao Xue, An-An Liu

机构 * The School of Electrical and Information Engineering, Tianjin University, China（天津大学电气与信息工程学院） ； Tiandy Technologies Co., Ltd, Tianjin, China（天津天盾科技有限公司） 纠错

专题命中 其他安全 ：safety(abstract)

Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models

Ronghuan Wu, Wanchao Su, Jing Liao

机构 * City University of Hong Kong（香港城市大学） ； Monash University（墨尔本大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments Project Page: https://chat2svg.github.io/