大模型对齐与安全 - arXivDaily 专题

2211.11446 2022-12-01 cs.CV cs.AI cs.CL 62%

SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training

Yuanze Lin, Chen Wei, Huiyu Wang, Alan Yuille, Cihang Xie

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

2202.07364 2022-12-01 cs.LG cs.AI cs.MA 62%

Zero-Shot Assistance in Sequential Decision Problems

Sebastiaan De Peuter, Samuel Kaski

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

Comments 9 pages, 8 appendix pages, 13 figures. Accepted for publication at AAAI-23

2211.16466 2022-11-30 cs.LG cs.AI cs.CV 62%

Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation

Miao Xiong, Shen Li, Wenjie Feng, Ailin Deng, Jihai Zhang, Bryan Hooi

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

Comments Published in Transactions on Machine Learning Research (TMLR) 2022

Journal ref Transactions on Machine Learning Research 08/2022

2205.11169 2022-11-23 cs.CV cs.AI cs.CL 62%

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Yuan Yao, Qianyu Chen, Ao Zhang, Wei Ji, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

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

Comments Accepted by EMNLP 2022

2210.16156 2022-11-17 cs.LG cs.AI cs.CV 62%

Reliability of CKA as a Similarity Measure in Deep Learning

MohammadReza Davari, Stefan Horoi, Amine Natik, Guillaume Lajoie, Guy Wolf, Eugene Belilovsky

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

2211.08192 2022-11-16 cs.CL cs.LG 62%

RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use

Pieter Delobelle, Thomas Winters, Bettina Berendt

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

Comments 9 pages, 1 figure, 3 tables

2211.07280 2022-11-15 cs.AI cs.CY 62%

A taxonomic system for failure cause analysis of open source AI incidents

Nikiforos Pittaras, Sean McGregor

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

2211.00677 2022-11-14 astro-ph.GA cs.AI cs.CV cs.LG 62%

Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection

Aleksandra Ćiprijanović, Ashia Lewis, Kevin Pedro, Sandeep Madireddy, Brian Nord, Gabriel N. Perdue, Stefan M. Wild

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

Comments 3 figures, 1 table; accepted to Machine Learning and the Physical Sciences - Workshop at the 36th conference on Neural Information Processing Systems (NeurIPS)

2211.03202 2022-11-08 cs.SD cs.AI cs.LG eess.AS stat.AP 62%

"Seeing Sound": Audio Classification with the Wigner-Wille Distribution and Convolutional Neural Networks

Antonios Marios Christonasis, Stef van Eijndhoven, Peter Duin

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

2211.02899 2022-11-08 cs.CL cs.AI 62%

Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing

Rui Yu, Yifeng Li, Wenpeng Lu, Longbing Cao

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

2211.01071 2022-11-03 cs.CL cs.LG 62%

Gradient Knowledge Distillation for Pre-trained Language Models

Lean Wang, Lei Li, Xu Sun

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

Comments Accepted by NeurIPS ENLSP 2022 workshop(spotlight)

2210.13617 2022-10-27 cs.CL cs.AI 62%

Adapters for Enhanced Modeling of Multilingual Knowledge and Text

Yifan Hou, Wenxiang Jiao, Meizhen Liu, Carl Allen, Zhaopeng Tu, Mrinmaya Sachan

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

Comments Our code, models, and data (e.g., integration corpus and extended datasets) are available: https://github.com/yifan-h/Multilingual_Space

2112.07356 2022-10-21 cs.AI cs.LG 62%

Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry

Karl Löwenmark, Cees Taal, Stephan Schnabel, Marcus Liwicki, Fredrik Sandin

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

2210.09215 2022-10-18 cs.CV cs.AI cs.LG 62%

A Systematic Review of Machine Learning Techniques for Cattle Identification: Datasets, Methods and Future Directions

Md Ekramul Hossain, Muhammad Ashad Kabir, Lihong Zheng, Dave L. Swain, Shawn McGrath, Jonathan Medway

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

Comments 34 pages, 14 figures

Journal ref Artificial Intelligence in Agriculture, Volume 6, 2022, Pages 138-155

2210.08119 2022-10-18 cs.RO cs.AI cs.LG cs.SI 62%

A Survey on Knowledge Graph-based Methods for Automated Driving

Juergen Luettin, Sebastian Monka, Cory Henson, Lavdim Halilaj

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

Comments Preprint to appear in KGSWC Knowledge Graph and Semantic Web Conference 2022

2107.04010 2022-09-30 cs.CY cs.LG stat.AP 62%

A Decision Support System for Safer Airplane Landings: Predicting Runway Conditions Using XGBoost and Explainable AI

Alise Danielle Midtfjord, Riccardo De Bin, Arne Bang Huseby

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

Journal ref Cold Regions Science and Technology, Volume 199, 2022

2209.13975 2022-09-29 cs.LG cs.AI 62%

Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications

K. Dmitriev, J. Schumann, F. Holzapfel

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

Journal ref 2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), 2021, pp. 1-7

2209.07065 2022-09-16 cs.SI cs.AI cs.CL 62%

CommunityLM: Probing Partisan Worldviews from Language Models

Hang Jiang, Doug Beeferman, Brandon Roy, Deb Roy

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

Comments Paper accepted by COLING 2022

2209.02984 2022-09-08 cs.HC cs.AI cs.LG 62%

Semantic Interactive Learning for Text Classification: A Constructive Approach for Contextual Interactions

Sebastian Kiefer, Mareike Hoffmann

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

2209.01558 2022-09-07 cs.LG cs.AI 62%

Scalable Adversarial Online Continual Learning

Tanmoy Dam, Mahardhika Pratama, MD Meftahul Ferdaus, Sreenatha Anavatti, Hussein Abbas

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

Comments has been accepted for publication at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2022 (ECML PKDD 2022)

2205.06936 2022-09-01 cs.LG cs.AI 62%

Efficient Learning of Interpretable Classification Rules

Bishwamittra Ghosh, Dmitry Malioutov, Kuldeep S. Meel

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

Comments 41 Pages, Published in JAIR Vol. 74 (2022)

Journal ref JAIR Vol. 74 (2022)

2208.12758 2022-08-29 cs.NE cs.AI cs.LG 62%

Quality Diversity Evolutionary Learning of Decision Trees

Andrea Ferigo, Leonardo Lucio Custode, Giovanni Iacca

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

2208.03188 2022-08-11 cs.CL cs.AI 62%

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

Kurt Shuster, Jing Xu, Mojtaba Komeili, Da Ju, Eric Michael Smith, Stephen Roller, Megan Ung, Moya Chen, Kushal Arora, Joshua Lane, Morteza Behrooz, William Ngan, Spencer Poff, Naman Goyal, Arthur Szlam, Y-Lan Boureau, Melanie Kambadur, Jason Weston

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

2101.05307 2022-07-20 cs.CV cs.AI cs.LG cs.RO 62%

Explainability of deep vision-based autonomous driving systems: Review and challenges

Éloi Zablocki, Hédi Ben-Younes, Patrick Pérez, Matthieu Cord

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

Comments IJCV 2022

2207.05078 2022-07-13 cs.LG cs.AI 62%

Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring

Al-Harith Farhad, Ioannis Sorokos, Andreas Schmidt, Mohammed Naveed Akram, Koorosh Aslansefat, Daniel Schneider

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

2207.01898 2022-07-06 cs.LG cs.AI 62%

"Even if ..." -- Diverse Semifactual Explanations of Reject

André Artelt, Barbara Hammer

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

2206.13034 2022-06-28 cs.LG cs.AI 62%

Monitoring Shortcut Learning using Mutual Information

Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai, Angus Galloway, H. R. Tizhoosh, Graham W. Taylor

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

Comments Accepted at ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability

2206.12770 2022-06-28 cs.CR cs.AI cs.LG 62%

Malware Detection and Prevention using Artificial Intelligence Techniques

Md Jobair Hossain Faruk, Hossain Shahriar, Maria Valero, Farhat Lamia Barsha, Shahriar Sobhan, Md Abdullah Khan, Michael Whitman, Alfredo Cuzzocreak, Dan Lo, Akond Rahman, Fan Wu

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

Journal ref 2021 IEEE International Conference on Big Data (Big Data)

2206.11381 2022-06-24 cs.LG cs.AI 62%

Prevent Car Accidents by Using AI

Sri Siddhartha Reddy Gudemupati, Yen Ling Chao, Lakshmi Praneetha Kotikalapudi, Ebrima Ceesay

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

2201.06961 2022-06-23 eess.SY cs.AI cs.LG cs.SY 62%

AI for Closed-Loop Control Systems -- New Opportunities for Modeling, Designing, and Tuning Control Systems

Julius Schöning, Adrian Riechmann, Hans-Jürgen Pfisterer

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

Comments 11 pages, 7 figures

1. 其他安全 8057 篇

SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training

Zero-Shot Assistance in Sequential Decision Problems

Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Reliability of CKA as a Similarity Measure in Deep Learning

RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use

A taxonomic system for failure cause analysis of open source AI incidents

Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection

"Seeing Sound": Audio Classification with the Wigner-Wille Distribution and Convolutional Neural Networks

Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing

Gradient Knowledge Distillation for Pre-trained Language Models

Adapters for Enhanced Modeling of Multilingual Knowledge and Text

Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry

A Systematic Review of Machine Learning Techniques for Cattle Identification: Datasets, Methods and Future Directions

A Survey on Knowledge Graph-based Methods for Automated Driving

A Decision Support System for Safer Airplane Landings: Predicting Runway Conditions Using XGBoost and Explainable AI

Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications

CommunityLM: Probing Partisan Worldviews from Language Models

Semantic Interactive Learning for Text Classification: A Constructive Approach for Contextual Interactions

Scalable Adversarial Online Continual Learning

Efficient Learning of Interpretable Classification Rules

Quality Diversity Evolutionary Learning of Decision Trees

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

Explainability of deep vision-based autonomous driving systems: Review and challenges

Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring

"Even if ..." -- Diverse Semifactual Explanations of Reject

Monitoring Shortcut Learning using Mutual Information

Malware Detection and Prevention using Artificial Intelligence Techniques

Prevent Car Accidents by Using AI

AI for Closed-Loop Control Systems -- New Opportunities for Modeling, Designing, and Tuning Control Systems