大模型对齐与安全 - arXivDaily 专题

2103.11070 2021-09-16 cs.CL 79%

Attribute Alignment: Controlling Text Generation from Pre-trained Language Models

Dian Yu, Zhou Yu, Kenji Sagae

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

Journal ref EMNLP 2021 Findings

2106.06381 2021-09-14 cs.CL 79%

Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment

Zewen Chi, Li Dong, Bo Zheng, Shaohan Huang, Xian-Ling Mao, Heyan Huang, Furu Wei

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

Comments ACL 2021

2103.00119 2021-06-17 cs.CV cs.LG 79%

ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation

Ali Pourramezan Fard, Hojjat Abdollahi, Mohammad Mahoor

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

Comments Accepted at CVPR 2021 Biometrics Workshop, jointly with the Workshop on Analysis and Modeling of Faces and Gestures

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 1521-1530

2012.01557 2021-06-14 cs.LG 79%

Value Alignment Verification

Daniel S. Brown, Jordan Schneider, Anca D. Dragan, Scott Niekum

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

Comments In proceedings International Conference on Machine Learning (ICML) 2021

2011.12428 2021-06-11 stat.ML cond-mat.dis-nn cs.LG cs.NE 79%

Align, then memorise: the dynamics of learning with feedback alignment

Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt

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

Comments The accompanying code for this paper is available at https://github.com/sdascoli/dfa-dynamics

Journal ref Proceedings of the 38th International Conference on Machine Learning (ICML), PMLR 139, 2021

2106.03619 2021-06-08 cs.AI 79%

Multi-modal Entity Alignment in Hyperbolic Space

Hao Guo, Jiuyang Tang, Weixin Zeng, Xiang Zhao, Li Liu

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

Comments 24 pages,5 figures;

2003.00260 2021-05-17 cs.AI stat.ML 79%

On Safety Assessment of Artificial Intelligence

Jens Braband, Hendrik Schäbe

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

Comments 16 pages, 7 figures

Journal ref Dependability, vol. 20 no. 4, 2020

2103.06244 2021-03-11 stat.ML cs.LG 79%

Multi-Class Multiple Instance Learning for Predicting Precursors to Aviation Safety Events

Marc-Henri Bleu-Laine, Tejas G. Puranik, Dimitri N. Mavris, Bryan Matthews

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

Comments 29 pages, 15 figures, 9 tables

2011.01631 2021-03-10 cs.LG cs.MM 79%

Robust Latent Representations via Cross-Modal Translation and Alignment

Vandana Rajan, Alessio Brutti, Andrea Cavallaro

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

Journal ref ICASSP 2021

2101.08385 2021-01-22 q-bio.GN cs.LG 79%

Motif Identification using CNN-based Pairwise Subsequence Alignment Score Prediction

Ethan Jacob Moyer, Anup Das

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

Comments 7 pages, 4 figures, submitted to the 2021 International Joint Conference on Neural Networks

2012.15184 2021-01-01 cs.SD cs.LG eess.AS 79%

Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis

Jose A. Gonzalez-Lopez, Miriam Gonzalez-Atienza, Alejandro Gomez-Alanis, Jose L. Perez-Cordoba, Phil D. Green

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

2010.15269 2020-11-13 eess.IV cs.CV cs.LG 79%

GloFlow: Global Image Alignment for Creation of Whole Slide Images for Pathology from Video

Viswesh Krishna, Anirudh Joshi, Philip L. Bulterys, Eric Yang, Andrew Y. Ng, Pranav Rajpurkar

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

Comments Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract

1901.06801 2020-11-03 cs.GT cs.LG 79%

Learning-Based Synthesis of Safety Controllers

Daniel Neider, Oliver Markgraf

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

2003.03167 2020-10-29 cs.CV cs.LG eess.IV 79%

When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs)

Victor Villena-Martinez, Sergiu Oprea, Marcelo Saval-Calvo, Jorge Azorin-Lopez, Andres Fuster-Guillo, Robert B. Fisher

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

Comments Published in Applied Sciences

Journal ref Appl. Sci. 2020, 10(21), 7524

2001.09768 2020-10-07 cs.CY 79%

Artificial Intelligence, Values and Alignment

Iason Gabriel

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

Journal ref Minds and Machines 2020

2008.08221 2020-08-20 cs.LG stat.ML 79%

Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunities

Zhaoyi Xu, Joseph Homer Saleh

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

Comments 50 pages

2007.13299 2020-07-29 eess.SP cs.LG 79%

Enhanced Beam Alignment for Millimeter Wave MIMO Systems: A Kolmogorov Model

Qiyou Duan, Taejoon Kim, Hadi Ghauch

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

Comments Submitted to the 2020 IEEE Globecom

2003.01197 2020-07-24 cs.RO cs.LG 79%

Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method

Wenhao Ding, Baiming Chen, Minjun Xu, Ding Zhao

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

Comments Accepted to IROS 2020

2007.05411 2020-07-13 cs.AI 79%

AGI Agent Safety by Iteratively Improving the Utility Function

Koen Holtman

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

Comments Part 1 of this work is a preprint of a conference paper to appear in: Proceedings of the 13th International Conference on Artificial General Intelligence (AGI-20), Springer LNAI 12177 (2020). Part 2 has additional, new research results that go beyond those in the conference paper

2005.13166 2020-05-28 cs.LG cs.CR stat.ML 79%

SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure

Koorosh Aslansefat, Ioannis Sorokos, Declan Whiting, Ramin Tavakoli Kolagari, Yiannis Papadopoulos

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

1910.10380 2020-03-02 eess.SY cs.AI cs.MA cs.SY 79%

Online Synthesis for Runtime Enforcement of Safety in Multi-Agent Systems

Dhananjay Raju, Suda Bharadwaj, Ufuk Topcu

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

2001.09612 2020-01-28 math.OC cs.LG cs.SY eess.SY stat.ML 79%

Optimization of Passive Chip Components Placement with Self-Alignment Effect for Advanced Surface Mounting Technology

Irandokht Parviziomran, Shun Cao, Haeyong Yang, Seungbae Park, Daehan Won

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

1912.09902 2019-12-23 cs.LG stat.ML 79%

Dependable Neural Networks for Safety Critical Tasks

Molly O'Brien, William Goble, Greg Hager, Julia Bukowski

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

Comments 8 pages, 4 figures. Accepted to AAAI EDSMLS Workshop 2020

1909.03464 2019-11-25 cs.CL stat.ML 79%

Back to the Future -- Sequential Alignment of Text Representations

Johannes Bjerva, Wouter Kouw, Isabelle Augenstein

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

Comments AAAI 2020

1904.04706 2019-11-22 cs.SE cs.LG 79%

Towards Safety Verification of Direct Perception Neural Networks

Chih-Hong Cheng, Chung-Hao Huang, Thomas Brunner, Vahid Hashemi

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

Comments Revised text (2nd version). The research work is conducted during the first author's service at the fortiss research institute and is supported by the following projects: "Audi Verifiable AI" from Audi AG, Germany and "Dependable AI for automotive systems" from DENSO Corporation, Japan

1906.11768 2019-11-05 stat.ML cs.LG 79%

Hierarchical Optimal Transport for Multimodal Distribution Alignment

John Lee, Max Dabagia, Eva L. Dyer, Christopher J. Rozell

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

1803.07658 2019-10-15 stat.ML cs.LG 79%

Graph-based regularization for regression problems with alignment and highly-correlated designs

Yuan Li, Benjamin Mark, Garvesh Raskutti, Rebecca Willett, Hyebin Song, David Neiman

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

1811.06746 2019-07-30 cs.LG stat.ML 79%

nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems

Chih-Hong Cheng, Chung-Hao Huang, Georg Nührenberg

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

Comments Tool available at https://github.com/dependable-ai/nn-dependability-kit

1808.09347 2019-04-24 cs.LG cs.CV stat.ML 79%

Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

Chao Chen, Zhihong Chen, Boyuan Jiang, Xinyu Jin

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

Comments This paper has been accepted by AAAI-2019

1808.05464 2019-04-03 cs.LG cs.HC q-bio.NC stat.ML 79%

Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach

He He, Dongrui Wu

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

1. 其他安全 7968 篇

Attribute Alignment: Controlling Text Generation from Pre-trained Language Models

Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment

ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation

Value Alignment Verification

Align, then memorise: the dynamics of learning with feedback alignment

Multi-modal Entity Alignment in Hyperbolic Space

On Safety Assessment of Artificial Intelligence

Multi-Class Multiple Instance Learning for Predicting Precursors to Aviation Safety Events

Robust Latent Representations via Cross-Modal Translation and Alignment

Motif Identification using CNN-based Pairwise Subsequence Alignment Score Prediction

Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis

GloFlow: Global Image Alignment for Creation of Whole Slide Images for Pathology from Video

Learning-Based Synthesis of Safety Controllers

When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs)

Artificial Intelligence, Values and Alignment

Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunities

Enhanced Beam Alignment for Millimeter Wave MIMO Systems: A Kolmogorov Model

Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method

AGI Agent Safety by Iteratively Improving the Utility Function

SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure

Online Synthesis for Runtime Enforcement of Safety in Multi-Agent Systems

Optimization of Passive Chip Components Placement with Self-Alignment Effect for Advanced Surface Mounting Technology

Dependable Neural Networks for Safety Critical Tasks

Back to the Future -- Sequential Alignment of Text Representations

Towards Safety Verification of Direct Perception Neural Networks

Hierarchical Optimal Transport for Multimodal Distribution Alignment

Graph-based regularization for regression problems with alignment and highly-correlated designs

nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems

Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach