大模型对齐与安全

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

David Boetius, Stefan Leue, Tobias Sutter

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Accepted at ICML 2023. 9 pages + 13 pages appendix, 8 figures

Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs

Tengfei Ma, Trong Nghia Hoang, Jie Chen

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

Human Control: Definitions and Algorithms

Ryan Carey, Tom Everitt

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

Comments UAI 2023

Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation

Jiawei Huang, Yi Ren, Rongjie Huang, Dongchao Yang, Zhenhui Ye, Chen Zhang, Jinglin Liu, Xiang Yin, Zejun Ma, Zhou Zhao

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

survAIval: Survival Analysis with the Eyes of AI

Kamil Kowol, Stefan Bracke, Hanno Gottschalk

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Code4Struct: Code Generation for Few-Shot Event Structure Prediction

Xingyao Wang, Sha Li, Heng Ji

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

Comments ACL 2023

Modelling Concurrency Bugs Using Machine Learning

Teodor Rares Begu

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 52 pages, 41 figures

Artificial Intelligence in 3GPP 5G-Advanced: A Survey

Xingqin Lin

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

Comments 7 pages; 6 figures; submitted for publication

A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues

Yunxin Li, Baotian Hu, Xinyu Chen, Yuxin Ding, Lin Ma, Min Zhang

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

Comments Accepted to ACL 2023 Main Conference

Refined Vision-Language Modeling for Fine-grained Multi-modal Pre-training

Lisai Zhang, Qingcai Chen, Zhijian Chen, Yunpeng Han, Zhonghua Li, Zhao Cao

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

Comments Work in progress, v0.2

Deconstructing deep active inference

Théophile Champion, Marek Grześ, Lisa Bonheme, Howard Bowman

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

Comments 59 pages, 46 figures

"Oops, Did I Just Say That?" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process

Pingchuan Ma, Zongjie Li, Ao Sun, Shuai Wang

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

Neural Stein critics with staged $L^2$-regularization

Matthew Repasky, Xiuyuan Cheng, Yao Xie

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

Nordic Vehicle Dataset (NVD): Performance of vehicle detectors using newly captured NVD from UAV in different snowy weather conditions

Hamam Mokayed, Amirhossein Nayebiastaneh, Kanjar De, Stergios Sozos, Olle Hagner, Bjorn Backe

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

Yuhang Li, Youngeun Kim, Hyoungseob Park, Priyadarshini Panda

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

Comments Published in Transactions on Machine Learning Research (TMLR)

Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models

Stephen Brade, Bryan Wang, Mauricio Sousa, Sageev Oore, Tovi Grossman

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

TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networks

Baixiang Huang, Bryan Hooi, Kai Shu

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 10 pages, 5 figures

Feature Learning and Signal Propagation in Deep Neural Networks

Yizhang Lou, Chris Mingard, Yoonsoo Nam, Soufiane Hayou

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

Comments 35 pages

Journal ref International Conference on Machine Learning. PMLR, 2022

Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA

Yongxin Zhu, Zhen Liu, Yukang Liang, Xin Li, Hao Liu, Changcun Bao, Linli Xu

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

Comments accepted in AAAI 2023

A Brief Review of Explainable Artificial Intelligence in Healthcare

Zahra Sadeghi, Roohallah Alizadehsani, Mehmet Akif Cifci, Samina Kausar, Rizwan Rehman, Priyakshi Mahanta, Pranjal Kumar Bora, Ammar Almasri, Rami S. Alkhawaldeh, Sadiq Hussain, Bilal Alatas, Afshin Shoeibi, Hossein Moosaei, Milan Hladik, Saeid Nahavandi, Panos M. Pardalos

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

BioSequence2Vec: Efficient Embedding Generation For Biological Sequences

Sarwan Ali, Usama Sardar, Murray Patterson, Imdad Ullah Khan

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

Comments Accepted to PAKDD 2023

Demo Alleviate: Demonstrating Artificial Intelligence Enabled Virtual Assistance for Telehealth: The Mental Health Case

Kaushik Roy, Vedant Khandelwal, Raxit Goswami, Nathan Dolbir, Jinendra Malekar, Amit Sheth

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Hallucinations in Large Multilingual Translation Models

Nuno M. Guerreiro, Duarte Alves, Jonas Waldendorf, Barry Haddow, Alexandra Birch, Pierre Colombo, André F. T. Martins

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Can Large Language Models assist in Hazard Analysis?

Simon Diemert, Jens H Weber

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning

Yatai Ji, Rongcheng Tu, Jie Jiang, Weijie Kong, Chengfei Cai, Wenzhe Zhao, Hongfa Wang, Yujiu Yang, Wei Liu

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

Comments CVPR 2023 accept

CoBIT: A Contrastive Bi-directional Image-Text Generation Model

Haoxuan You, Mandy Guo, Zhecan Wang, Kai-Wei Chang, Jason Baldridge, Jiahui Yu

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

Comments 14 pages, 5 figures

A Survey of Demonstration Learning

André Correia, Luís A. Alexandre

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 35 pages, 9 figures

Web and Mobile Platforms for Managing Elections based on IoT And Machine Learning Algorithms

G. M. I. K. Galagoda, W. M. C. A. Karunarathne, R. S. Bates, K. M. H. V. P. Gangathilaka, Kanishka Yapa, Erandika Gamage

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Journal ref International Journal of Engineering Applied Sciences and Technology, 2022, Vol 7, No 7, 29-35

Predicted Embedding Power Regression for Large-Scale Out-of-Distribution Detection

Hong Yang, William Gebhardt, Alexander G. Ororbia, Travis Desell

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Conflict-Based Search for Explainable Multi-Agent Path Finding

Justin Kottinger, Shaull Almagor, Morteza Lahijanian

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments To appear in International Conference on Automated Planning and Scheduling (ICAPS 2022), June 2022

Journal ref 2022 Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS))