大模型对齐与安全

Liability regimes in the age of AI: a use-case driven analysis of the burden of proof

David Fernández Llorca, Vicky Charisi, Ronan Hamon, Ignacio Sánchez, Emilia Gómez

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

Comments Paper published at the Journal of Artificial Intelligence Research

Journal ref Journal of Artificial Intelligence Research, Vol. 76 (2023), pp. 613-644

Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions

Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency

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

RoentGen: Vision-Language Foundation Model for Chest X-ray Generation

Pierre Chambon, Christian Bluethgen, Jean-Benoit Delbrouck, Rogier Van der Sluijs, Małgorzata Połacin, Juan Manuel Zambrano Chaves, Tanishq Mathew Abraham, Shivanshu Purohit, Curtis P. Langlotz, Akshay Chaudhari

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

Comments 19 pages

Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence

Peter Stone, Rodney Brooks, Erik Brynjolfsson, Ryan Calo, Oren Etzioni, Greg Hager, Julia Hirschberg, Shivaram Kalyanakrishnan, Ece Kamar, Sarit Kraus, Kevin Leyton-Brown, David Parkes, William Press, AnnaLee Saxenian, Julie Shah, Milind Tambe, Astro Teller

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

Comments 52 pages, https://ai100.stanford.edu/2016-report

GERNERMED++: Transfer Learning in German Medical NLP

Johann Frei, Ludwig Frei-Stuber, Frank Kramer

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

LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging

Andy Rosenbaum, Saleh Soltan, Wael Hamza, Yannick Versley, Markus Boese

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

Comments Accepted to The 29th International Conference on Computational Linguistics (COLING 2022) October 12-17, 2022, Gyeongju, Republic of Korea https://coling2022.org/

TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks

Ruofan Hu, Dongyu Zhang, Dandan Tao, Thomas Hartvigsen, Hao Feng, Elke Rundensteiner

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

Comments LREC 2022

Blockchain associated machine learning and IoT based hypoglycemia detection system with auto-injection feature

Rahnuma Mahzabin, Fahim Hossain Sifat, Sadia Anjum, Al-Akhir Nayan, Muhammad Golam Kibria

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

Journal ref Indonesian Journal of Electrical Engineering and Computer Science, Vol. 27, No. 1, pp. 447-455, July 2022

Learning Models of Individual Behavior in Chess

Reid McIlroy-Young, Russell Wang, Siddhartha Sen, Jon Kleinberg, Ashton Anderson

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

Comments 12 pages, 11 figures, 5 tables, Published in the Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022), Code https://github.com/CSSLab/maia-individual

SKILL: Structured Knowledge Infusion for Large Language Models

Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi

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

Comments NAACL 2022

Bilingual Lexicon Induction through Unsupervised Machine Translation

Mikel Artetxe, Gorka Labaka, Eneko Agirre

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

Comments ACL 2019

Matching with Transformers in MELT

Sven Hertling, Jan Portisch, Heiko Paulheim

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

Comments accepted at the Ontology Matching Workshop at the International Semantic Web Conference (ISWC 2021)

A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space

Alex Jones, William Yang Wang, Kyle Mahowald

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

Comments 15 pages, 8 figures, EMNLP 2021

Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data

Massimo Nicosia, Zhongdi Qu, Yasemin Altun

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

Comments Accepted to EMNLP 2021 (Findings)

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, Rosanne Liu

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

Comments ICLR 2020 camera ready

Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs

Lingbing Guo, Zequn Sun, Wei Hu

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

Comments Accepted by the 36th International Conference on Machine Learning (ICML 2019)

A spelling correction model for end-to-end speech recognition

Jinxi Guo, Tara N. Sainath, Ron J. Weiss

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

Comments Accepted to ICASSP 2019

Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models

Takashi Wada, Tomoharu Iwata

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

Comments 8 pages

Representation Learning for Grounded Spatial Reasoning

Michael Janner, Karthik Narasimhan, Regina Barzilay

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

Comments Accepted to TACL 2017, code: https://github.com/jannerm/spatial-reasoning

End-to-End Attention-based Large Vocabulary Speech Recognition

Dzmitry Bahdanau, Jan Chorowski, Dmitriy Serdyuk, Philemon Brakel, Yoshua Bengio

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

Symmetry-Breaking Augmentations for Ad Hoc Teamwork

Ravi Hammond, Dustin Craggs, Mingyu Guo, Jakob Foerster, Ian Reid

机构 * Foerster Lab for AI Research, University of Oxford（牛津大学人工智能研究实验室） ； Australian Institute for Machine Learning, University of Adelaide（阿德莱德大学人工智能研究所） ； Meta AI Research, UK（英国Meta人工智能研究） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

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

Comments 21 pages, 12 figures, Bidirectional Human-AI Alignment workshop, ICLR 2025

Towards Controllable Agent in MOBA Games with Generative Modeling

Shubao Zhang

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

Comments Human-Compatible AI; Human-AI Cooperation; AI control; AI Alignment

Improved Multilingual Language Model Pretraining for Social Media Text via Translation Pair Prediction

Shubhanshu Mishra, Aria Haghighi

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

Comments Camera ready version. Accepted to WNUT 2021. Code for reproducing the experiments can be found at: https://github.com/twitter-research/multilingual-alignment-tpp

Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening

用于胎儿脑室体积测量与异常筛查的跨模态超声-MRI学习

Yuhao Huang, Yuanji Zhang, Yuhuan Lu, Dong Ni, P. Ellen Grant, Davood Karimi

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

AI总结 本研究提出跨模态学习框架VIFBA，基于超声视频实现胎儿脑室体积预测、VM严重程度分类及非VM异常筛查，性能优于基线与现有模型，为产前脑筛查提供实用方案。

Comments 17 pages, 11 figures, 6 tables

Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans

匹配结果，不同注视：中央凹多模态大语言模型（MLLM）的搜索方式与人类的对比

Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Ulas Bagci, Alessandro Bruno

机构 * F-initiatives（F计划） ； Université Sorbonne Paris Nord（巴黎北索邦大学） ； Northwestern University（西北大学） ； IULM university（IULM大学） 纠错

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

AI总结 研究对比三款通用MLLM与人类在目标导向视觉搜索中的表现，发现模型在决策和目标获取上优于人类，但注视过程与人类不同，现有指标无法验证类人视觉，零样本模型不适用于过程层面问题。

Comments Paper accepted at 3rd HCV workshop at ECCV 2026. 12 pages main text, 16 pages supp

Architecture-Dependent Causal Transfer of Activation States Across Large Language Models

大语言模型间激活状态的架构依赖型因果迁移

Fernando Cardenas Piepereit

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

AI总结 本文探究大语言模型间激活状态的因果迁移，发现该迁移依赖模型架构，仅部分仅解码器模型对可实现具统计显著性的因果效应，且迁移的是表征载体而非意义。

Comments 13 pages, 3 tables

Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment

面向小型设备的大模型：边缘AI部署的最新进展与实证分析

Subhransu Das, Jiaming Cheng, Arnav Kumar, Sadia Afrose, Mingzhe Han, Michael Silagy, Shreya Palande, Brijesh Soni, Rajiv Ramnath

机构 * The Ohio State University（俄亥俄州立大学） 纠错

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

AI总结 本文调研近期边缘AI部署研究，提炼指南并在多平台测试，发现不同任务适用不同压缩技术，剪枝可能提升分割性能但会增加延迟，相关成果已开源。

Comments Parts of this work were presented at the IEEE Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA, January 2026

EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory

EgoCITE：面向长时程自我中心记忆的上下文增强索引与时序感知检索

Le Zhang, Ke Sun

机构 * University of Michigan（密歇根大学） 纠错

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

AI总结 本研究针对长时程自我中心记忆系统的索引不可靠、忽略时序意图的问题，提出EgoCITE框架，经多数据集评估，其准确率优于基线且成本显著低于长上下文LLM智能体。

Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning

通过激活引导剪枝实现跨模型规模的无训练知识迁移

Jiahe Fan, Si Chen, Yinghao Hou, Aiyuan Zhang, Hong Xie

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

AI总结 本文提出激活剪枝融合框架APM，通过激活引导选择源模型的显著组件并注入目标模型，无需训练和显式语义对齐，在16个基准上将3B目标模型平均准确率从55.5%提升至60.6%。

Comments 9 pages, 3 figures, and 7 tables

Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples

面向红外光谱化学传感与分析的仿真到真实迁移学习：从分子到复杂样品

Yusen Tan, Yixuan Chen, Zheng Fang, Pan Liu, Yifan Li, Qinyu Guo, Zhedong Lin, Yuqiang Li, Xiangxiang Zeng, Tong Wang, Jun Xia

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Jilin University（吉林大学） ； University of Auckland（奥克兰大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Hunan University（湖南大学） ； The Hong Kong University of Science and Technology（香港科技大学） 纠错

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

AI总结 研究针对红外光谱化学传感的迁移难题，提出超1亿参数的红外光谱基础模型UltraIR，经6000万仿真光谱预训练后，在多类化学分析任务中性能优于基线，且适配性与数据效率优异。