大模型对齐与安全 - arXivDaily 专题

2012.05876 2020-12-18 cs.AI cs.LG 62%

Neurosymbolic AI: The 3rd Wave

Artur d'Avila Garcez, Luis C. Lamb

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

Comments 37 pages

2010.07523 2020-12-15 cs.CL cs.AI 62%

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

Zhengxuan Wu, Desmond C. Ong

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

Journal ref AAAI 2021

2012.02012 2020-12-04 cs.CL cs.LG cs.SD eess.AS 62%

End to End ASR System with Automatic Punctuation Insertion

Yushi Guan

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

2006.04950 2020-12-02 cs.CY cs.LG 62%

Machine Learning Systems for Intelligent Services in the IoT: A Survey

Wiebke Toussaint, Aaron Yi Ding

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

Comments Requires rework

2011.01771 2020-11-06 cs.LG cs.AI cs.SY eess.SY 62%

Deep Reinforcement Learning Based Dynamic Route Planning for Minimizing Travel Time

Yuanzhe Geng, Erwu Liu, Rui Wang, Yiming Liu

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

2010.15065 2020-10-29 q-bio.BM cs.CL cs.LG 62%

Fixed-Length Protein Embeddings using Contextual Lenses

Amir Shanehsazzadeh, David Belanger, David Dohan

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

2010.11940 2020-10-23 cs.RO cs.AI cs.LG 62%

Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments

Jun Yamada, Youngwoon Lee, Gautam Salhotra, Karl Pertsch, Max Pflueger, Gaurav S. Sukhatme, Joseph J. Lim, Peter Englert

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

Comments Published at the Conference on Robot Learning (CoRL) 2020

2010.02726 2020-10-07 cs.CY cs.AI 62%

Legal Sentiment Analysis and Opinion Mining (LSAOM): Assimilating Advances in Autonomous AI Legal Reasoning

Lance Eliot

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

Comments 26 pages, 8 figures. arXiv admin note: text overlap with arXiv:2009.14620

1907.10662 2020-10-05 cs.LG cs.AI cs.PL cs.SC stat.ML 62%

ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks

Xuankang Lin, He Zhu, Roopsha Samanta, Suresh Jagannathan

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

Comments FMCAD'20

2005.00200 2020-10-01 cs.CV cs.CL cs.LG 62%

HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training

Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan, Licheng Yu, Jingjing Liu

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

Comments Accepted by EMNLP 2020

2008.12615 2020-09-16 cs.CY cs.AI 62%

An Impact Model of AI on the Principles of Justice: Encompassing the Autonomous Levels of AI Legal Reasoning

Lance Eliot

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

Comments 19 pages, 6 figures. arXiv admin note: text overlap with arXiv:2008.10575, arXiv:2008.09507, arXiv:2008.07743

2002.06353 2020-09-16 cs.CV cs.CL cs.LG eess.AS eess.IV 62%

UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation

Huaishao Luo, Lei Ji, Botian Shi, Haoyang Huang, Nan Duan, Tianrui Li, Jason Li, Taroon Bharti, Ming Zhou

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

2008.07434 2020-08-18 cs.LG cs.AI 62%

Integrating Deep Reinforcement Learning Networks with Health System Simulations

Michael Allen, Thomas Monks

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

Comments 6 pages, 1 figure

1909.11740 2020-07-21 cs.CV cs.CL cs.LG 62%

UNITER: UNiversal Image-TExt Representation Learning

Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu

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

Comments ECCV 2020

2006.04748 2020-06-09 cs.CY cs.LG q-bio.QM 62%

Serverless on FHIR: Deploying machine learning models for healthcare on the cloud

Bell Raj Eapen, Kamran Sartipi, Norm Archer

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

Comments 10 pages, 1 figure

2006.04300 2020-06-09 cs.CY cs.LG 62%

Machine Learning Interpretability and Its Impact on Smart Campus Projects

Raghad Zenki, Mu Mu

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

2005.10049 2020-05-21 eess.AS cs.CL cs.LG cs.SD stat.ML 62%

Early Stage LM Integration Using Local and Global Log-Linear Combination

Wilfried Michel, Ralf Schlüter, Hermann Ney

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

Comments Submitted to Interspeech 2020

1810.07382 2020-05-21 cs.CL cs.IR cs.LG cs.NE stat.ML 62%

Analysis of Railway Accidents' Narratives Using Deep Learning

Mojtaba Heidarysafa, Kamran Kowsari, Laura E. Barnes, Donald E. Brown

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

Comments accepted in IEEE International Conference on Machine Learning and Applications (IEEE ICMLA)

2004.07928 2020-04-20 cs.LG cs.AI stat.ML 62%

MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library

Dmitry Kazhdan, Zohreh Shams, Pietro Liò

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

Comments Presented at the KR2ML workshop at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

2004.01655 2020-04-06 cs.CL cs.LG stat.ML 62%

Aligned Cross Entropy for Non-Autoregressive Machine Translation

Marjan Ghazvininejad, Vladimir Karpukhin, Luke Zettlemoyer, Omer Levy

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

1910.06772 2020-03-17 stat.ML cs.AI cs.LG 62%

Counterfactual diagnosis

Jonathan G. Richens, Ciaran M. Lee, Saurabh Johri

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

Comments Restructured and new subsections. Improved figures. Introduction rewritten

1909.06349 2020-03-03 cs.LG cs.AI stat.ML 62%

Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

Vincent S. Chen, Sen Wu, Zhenzhen Weng, Alexander Ratner, Christopher Ré

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

Comments NeurIPS 2019

2002.02000 2020-02-07 cs.CL cs.LG 62%

Aligning the Pretraining and Finetuning Objectives of Language Models

Nuo Wang Pierse, Jingwen Lu

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

Comments 8 pages, 2 figures and 6 tables. Submitted to ICML 2020

1807.06736 2020-01-14 cs.CL cs.LG cs.SD eess.AS 62%

Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis

Jing-Xuan Zhang, Zhen-Hua Ling, Li-Rong Dai

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

Comments 5 pages, 3 figures, 2 tables. Published in IEEE International Conference on Acoustics, Speech and Signal Processing 2018 (ICASSP2018)

Journal ref IEEE International Conference on Acoustics, Speech and Signal Processing (2018) 4789-4793

1908.07490 2019-12-05 cs.CL cs.CV cs.LG 62%

LXMERT: Learning Cross-Modality Encoder Representations from Transformers

Hao Tan, Mohit Bansal

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

Comments EMNLP 2019 (14 pages; with new attention visualizations)

1907.10508 2019-07-25 cs.CY cs.AI 62%

A system of different layers of abstraction for artificial intelligence

Alexander Serb, Themistoklis Prodromakis

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

Comments 12 pages, 1 figure, 1 table, submitted version

1904.08311 2019-07-03 cs.CL cs.AI 62%

Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation

Gakuto Kurata, Kartik Audhkhasi

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

Comments Accepted to Interspeech 2019

1906.01702 2019-06-06 cs.CL cs.LG 62%

Improving Neural Language Models by Segmenting, Attending, and Predicting the Future

Hongyin Luo, Lan Jiang, Yonatan Belinkov, James Glass

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

Comments Accepted by ACL 2019

1903.10654 2019-05-28 cs.LG cs.AI cs.RO 62%

Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving

Akifumi Wachi

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

1905.05637 2019-05-15 cs.RO cs.AI cs.LG 62%

Randomized Adversarial Imitation Learning for Autonomous Driving

MyungJae Shin, Joongheon Kim

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

Journal ref International Joint Conference on Artificial Intelligence (IJCAI) 2019

1. 其他安全 8057 篇

Neurosymbolic AI: The 3rd Wave

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

End to End ASR System with Automatic Punctuation Insertion

Machine Learning Systems for Intelligent Services in the IoT: A Survey

Deep Reinforcement Learning Based Dynamic Route Planning for Minimizing Travel Time

Fixed-Length Protein Embeddings using Contextual Lenses

Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments

Legal Sentiment Analysis and Opinion Mining (LSAOM): Assimilating Advances in Autonomous AI Legal Reasoning

ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks

HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training

An Impact Model of AI on the Principles of Justice: Encompassing the Autonomous Levels of AI Legal Reasoning

UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation

Integrating Deep Reinforcement Learning Networks with Health System Simulations

UNITER: UNiversal Image-TExt Representation Learning

Serverless on FHIR: Deploying machine learning models for healthcare on the cloud

Machine Learning Interpretability and Its Impact on Smart Campus Projects

Early Stage LM Integration Using Local and Global Log-Linear Combination

Analysis of Railway Accidents' Narratives Using Deep Learning

MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library

Aligned Cross Entropy for Non-Autoregressive Machine Translation

Counterfactual diagnosis

Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

Aligning the Pretraining and Finetuning Objectives of Language Models

Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis

LXMERT: Learning Cross-Modality Encoder Representations from Transformers

A system of different layers of abstraction for artificial intelligence

Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation

Improving Neural Language Models by Segmenting, Attending, and Predicting the Future

Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving

Randomized Adversarial Imitation Learning for Autonomous Driving