大模型对齐与安全

Bridging Language Gaps: Enhancing Few-Shot Language Adaptation

Philipp Borchert, Jochen De Weerdt, Marie-Francine Moens

机构 * IESEG School of Management（IESEG管理学院） ； Research Centre for Information Systems Engineering（信息系统工程研究中心） ； Department of Computer Science（计算机科学系） 纠错

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

Comments 17 pages

NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs

Davorin Miličević, Ratko Grbić

机构 * Faculty of Electrical Engineering, Computer Science and Information Technology Osijek（电子工程、计算机科学与信息技术学院奥斯杰克） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 13 pages, 4 figures. Submitted to Elsevier Neurocomputing, under review

Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception

Yang Li, Quan Yuan, Guiyang Luo, Xiaoyuan Fu, Rui Pan, Yujia Yang, Congzhang Shao, Yuewen Liu, Jinglin Li

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

Orchid: Orchestrating Context Across Creative Workflows with Generative AI

Srishti Palani, Gonzalo Ramos

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

Seeing Like a Designer Without One: A Study on Unsupervised Slide Quality Assessment via Designer Cue Augmentation

Tai Inui, Steven Oh, Magdeline Kuan

机构 * Waseda University（早稻田大学） 纠错

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

Comments 6 pages

Towards detecting Primordial non-Gaussianity in the CMB using Spherical Convolutional Neural Networks

Jorik Melsen, Thomas Flöss, P. Daniel Meerburg

专题命中 其他安全 ：alignment(abstract)

Comments 11 pages, 1 figure, prepared for submission to MNRAS

Journal ref Mon Not R Astron Soc (2025) 3269-3279