大模型对齐与安全 - arXivDaily 专题

2109.12178 2021-09-28 cs.CV cs.AI cs.LG 62%

MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling

Tarik Arici, Mehmet Saygin Seyfioglu, Tal Neiman, Yi Xu, Son Train, Trishul Chilimbi, Belinda Zeng, Ismail Tutar

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

2109.11295 2021-09-24 cs.CL cs.LG 62%

Dynamic Knowledge Distillation for Pre-trained Language Models

Lei Li, Yankai Lin, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun

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

Comments Main Conference EMNLP 2021, Camera Ready

2108.08236 2021-09-20 cs.CV cs.AI cs.LG cs.MA cs.RO 62%

LOKI: Long Term and Key Intentions for Trajectory Prediction

Harshayu Girase, Haiming Gang, Srikanth Malla, Jiachen Li, Akira Kanehara, Karttikeya Mangalam, Chiho Choi

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

Comments ICCV 2021 (The dataset is available at https://usa.honda-ri.com/loki)

2109.07458 2021-09-16 cs.CL cs.LG 62%

Comparing Text Representations: A Theory-Driven Approach

Gregory Yauney, David Mimno

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

Journal ref Published in EMNLP 2021

2109.05893 2021-09-14 cs.IT cs.AI cs.LG math.IT 62%

Learning-Based UE Classification in Millimeter-Wave Cellular Systems With Mobility

Dino Pjanić, Alexandros Sopasakis, Harsh Tataria, Fredrik Tufvesson, Andres Reial

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

Comments Accepted for Publication in 2021 IEEE International Workshop on Machine Learning for Signal Processing, 6 Pages, 7 Figures, 1 Table

2108.09402 2021-08-24 cs.LG cs.AI cs.SI 62%

A Multi-Task Learning Framework for COVID-19 Monitoring and Prediction of PPE Demand in Community Health Centres

Bonaventure Chidube Molokwu, Shaon Bhatta Shuvo, Ziad Kobti, Anne Snowdon

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

Comments 6-page article/manuscript

2108.08995 2021-08-23 cs.CV cs.AI cs.LG 62%

Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization

Mohammad Mahfujur Rahman, Clinton Fookes, Sridha Sridharan

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

Comments This manuscript is submitted to Computer Vision and Image Understanding (CVIU)

2108.02076 2021-08-05 cs.SE cs.AI cs.LG 62%

The Potential of Using Vision Videos for CrowdRE: Video Comments as a Source of Feedback

Oliver Karras, Eklekta Kristo, Jil Klünder

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

Comments Accepted for publication at 2021 IEEE 29th International Requirements Engineering Conference Workshops (REW)

2107.05216 2021-07-13 cs.LG cs.AI 62%

A Simple Reward-free Approach to Constrained Reinforcement Learning

Sobhan Miryoosefi, Chi Jin

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

2107.02025 2021-07-06 cs.CL cs.LG cs.SI 62%

Textual Data Distributions: Kullback Leibler Textual Distributions Contrasts on GPT-2 Generated Texts, with Supervised, Unsupervised Learning on Vaccine & Market Topics & Sentiment

Jim Samuel, Ratnakar Palle, Eduardo Correa Soares

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

2106.13364 2021-06-28 cs.AI cs.CV cs.LG 62%

CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning

Daniel McDuff, Yale Song, Jiyoung Lee, Vibhav Vineet, Sai Vemprala, Nicholas Gyde, Hadi Salman, Shuang Ma, Kwanghoon Sohn, Ashish Kapoor

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

2006.08164 2021-06-24 cs.CY cs.AI 62%

COVID-19 Vaccine Acceptance in the US and UK in the Early Phase of the Pandemic: AI-Generated Vaccines Hesitancy for Minors, and the Role of Governments

Gabriel Lima, Meeyoung Cha, Chiyoung Cha, Hyeyoung Hwang

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

Comments Published to the Journal of the Korean Data Analysis Society vol. 23 no. 3

2106.08064 2021-06-16 cs.LG cs.AI 62%

Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approach

Johannes Rabold, Michael Siebers, Ute Schmid

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

2105.14167 2021-06-11 cs.CL cs.AI 62%

NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning

Zeming Chen, Qiyue Gao, Lawrence S. Moss

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

Comments 8 pages, 4 figures, The 10th Joint Conference on Lexical and Computational Semantics (*SEM2021) @ ACL2021

2106.02567 2021-06-07 cs.CV cs.AI cs.LG 62%

AI Driven Road Maintenance Inspection

Ratnajit Mukherjee, Haris Iqbal, Shabbir Marzban, Ahmed Badar, Terence Brouns, Shruthi Gowda, Elahe Arani, Bahram Zonooz

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

Comments accepted at 27th ITS World Congress, 2021

2005.00743 2021-05-25 cs.CL cs.IR cs.LG 62%

Synthesizer: Rethinking Self-Attention in Transformer Models

Yi Tay, Dara Bahri, Donald Metzler, Da-Cheng Juan, Zhe Zhao, Che Zheng

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

Comments ICML 2021

2104.01543 2021-05-12 cs.CL cs.AI cs.HC 62%

A Conversational Agent System for Dietary Supplements Use

Esha Singh, Anu Bompelli, Ruyuan Wan, Jiang Bian, Serguei Pakhomov, Rui Zhang

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

2101.06832 2021-04-30 cs.CV cs.AI cs.LG cs.RO 62%

Deep Structured Reactive Planning

Jerry Liu, Wenyuan Zeng, Raquel Urtasun, Ersin Yumer

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

Comments ICRA 2021

2003.14056 2021-04-15 cs.CL cs.LG 62%

Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent Neural Networks

Prajit Dhar, Arianna Bisazza

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

Comments v3: Submitted to NaDaLiDa 2021. 9 pages, two columns and with 6 figures and 1 table

2010.12283 2021-04-13 cs.CL cs.LG 62%

ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding

Minjeong Kim, Gyuwan Kim, Sang-Woo Lee, Jung-Woo Ha

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

Comments ICASSP 2021; 5 pages

2104.00739 2021-04-05 cs.SE cs.AI cs.LG cs.PL q-bio.OT 62%

Formal Methods for the Informal Engineer: Workshop Recommendations

Gopal Sarma, James Koppel, Gregory Malecha, Patrick Schultz, Eric Drexler, Ramana Kumar, Cody Roux, Philip Zucker

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

Comments 6 pages

2103.09050 2021-03-17 cs.CY cs.LG 62%

Hate, Obscenity, and Insults: Measuring the Exposure of Children to Inappropriate Comments in YouTube

Sultan Alshamrani, Ahmed Abusnaina, Mohammed Abuhamad, Daehun Nyang, David Mohaisen

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

2008.02516 2021-03-16 eess.AS cs.CL cs.CV cs.LG cs.SD 62%

FastLR: Non-Autoregressive Lipreading Model with Integrate-and-Fire

Jinglin Liu, Yi Ren, Zhou Zhao, Chen Zhang, Baoxing Huai, Nicholas Jing Yuan

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

Comments Accepted by ACM MM 2020

2102.01564 2021-02-03 cs.LG cs.AI 62%

Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)

Richard Hawkins, Colin Paterson, Chiara Picardi, Yan Jia, Radu Calinescu, Ibrahim Habli

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

2102.00290 2021-02-02 cs.CL cs.LG 62%

Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks

Maurício Gruppi, Sibel Adalı, Pin-Yu Chen

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

Comments Published at AAAI-2021

2101.01418 2021-01-29 cs.CV cs.AI cs.LG cs.SY eess.SY 62%

Support Vector Machine and YOLO for a Mobile Food Grading System

Lili Zhu, Petros Spachos

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

1906.09323 2021-01-29 cs.LG cs.AI cs.GT stat.ML 62%

Reinforcement Learning with Convex Constraints

Sobhan Miryoosefi, Kianté Brantley, Hal Daumé, Miroslav Dudik, Robert Schapire

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

Journal ref Advances in Neural Information Processing Systems 32 (2019), 14093-14102

2101.10649 2021-01-27 cs.CL cs.AI 62%

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

Hyunjin Choi, Judong Kim, Seongho Joe, Seungjai Min, Youngjune Gwon

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

Comments 6 pages, 4 figures, to be published in 25th International Conference on Pattern Recognition, ICPR 2020

2101.03613 2021-01-12 cs.LG cs.AI 62%

Explainable Artificial Intelligence (XAI): An Engineering Perspective

F. Hussain, R. Hussain, E. Hossain

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

2012.14359 2020-12-29 cs.AI cs.CV cs.LG cs.RO 62%

Commonsense Visual Sensemaking for Autonomous Driving: On Generalised Neurosymbolic Online Abduction Integrating Vision and Semantics

Jakob Suchan, Mehul Bhatt, Srikrishna Varadarajan

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

Comments This is a preprint / review version of an accepted contribution to be published as part of the Artificial Intelligence Journal (AIJ).? The article is an extended version of an IJCAI 2019 publication [74, arXiv:1906.00107]

1. 其他安全 8057 篇

MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling

Dynamic Knowledge Distillation for Pre-trained Language Models

LOKI: Long Term and Key Intentions for Trajectory Prediction

Comparing Text Representations: A Theory-Driven Approach

Learning-Based UE Classification in Millimeter-Wave Cellular Systems With Mobility

A Multi-Task Learning Framework for COVID-19 Monitoring and Prediction of PPE Demand in Community Health Centres

Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization

The Potential of Using Vision Videos for CrowdRE: Video Comments as a Source of Feedback

A Simple Reward-free Approach to Constrained Reinforcement Learning

Textual Data Distributions: Kullback Leibler Textual Distributions Contrasts on GPT-2 Generated Texts, with Supervised, Unsupervised Learning on Vaccine & Market Topics & Sentiment

CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning

COVID-19 Vaccine Acceptance in the US and UK in the Early Phase of the Pandemic: AI-Generated Vaccines Hesitancy for Minors, and the Role of Governments

Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approach

NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning

AI Driven Road Maintenance Inspection

Synthesizer: Rethinking Self-Attention in Transformer Models

A Conversational Agent System for Dietary Supplements Use

Deep Structured Reactive Planning

Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent Neural Networks

ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding

Formal Methods for the Informal Engineer: Workshop Recommendations

Hate, Obscenity, and Insults: Measuring the Exposure of Children to Inappropriate Comments in YouTube

FastLR: Non-Autoregressive Lipreading Model with Integrate-and-Fire

Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)

Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks

Support Vector Machine and YOLO for a Mobile Food Grading System

Reinforcement Learning with Convex Constraints

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

Explainable Artificial Intelligence (XAI): An Engineering Perspective

Commonsense Visual Sensemaking for Autonomous Driving: On Generalised Neurosymbolic Online Abduction Integrating Vision and Semantics