大模型对齐与安全 - arXivDaily 专题

2209.02982 2022-12-01 cs.CL 57%

Improving the Cross-Lingual Generalisation in Visual Question Answering

Farhad Nooralahzadeh, Rico Sennrich

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments This work is accepted by the AAAI 2023

2211.14889 2022-11-29 cs.LG cs.SY eess.SY 57%

Machine Learning for Smart and Energy-Efficient Buildings

Hari Prasanna Das, Yu-Wen Lin, Utkarsha Agwan, Lucas Spangher, Alex Devonport, Yu Yang, Jan Drgona, Adrian Chong, Stefano Schiavon, Costas J. Spanos

专题命中其他安全：safety(abstract)；分类 cs.LG

2211.13594 2022-11-28 cs.CV cs.AI 57%

Self-supervised vision-language pretraining for Medical visual question answering

Pengfei Li, Gang Liu, Lin Tan, Jinying Liao, Shenjun Zhong

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments 5 pages, 3 figures

2111.06978 2022-11-28 cs.NI cs.LG 57%

RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN

Peizheng Li, Jonathan Thomas, Xiaoyang Wang, Ahmed Khalil, Abdelrahim Ahmad, Rui Inacio, Shipra Kapoor, Arjun Parekh, Angela Doufexi, Arman Shojaeifard, Robert Piechocki

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments 17 pages, 6 figrues

Journal ref IEEE Access (2022), vol. 10, pp. 113808-113826

2211.10546 2022-11-23 cs.LG q-bio.BM 57%

Evaluating COVID-19 Sequence Data Using Nearest-Neighbors Based Network Model

Sarwan Ali

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments Accepted at IEEE BigData 2022

2211.11520 2022-11-22 cs.RO cs.LG 57%

Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile Robot

Michael Yuhas, Arvind Easwaran

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments 3 pages, 5 figures, RTSS 2022

2203.01644 2022-11-22 cs.CL 57%

UDAAN: Machine Learning based Post-Editing tool for Document Translation

Ayush Maheshwari, Ajay Ravindran, Venkatapathy Subramanian, Ganesh Ramakrishnan

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments Demo paper at CoDS-COMAD 2023. Vist project website at https://udaanproject.org

2101.01519 2022-11-22 stat.ML cs.LG math.OC 57%

Handling Hard Affine SDP Shape Constraints in RKHSs

Pierre-Cyril Aubin-Frankowski, Zoltan Szabo

专题命中其他安全：safety(abstract)；分类 cs.LG

Journal ref Journal of Machine Learning Research 23 (2022) 1-53

2211.07697 2022-11-16 cs.LG cs.CV math.AT 57%

Do Neural Networks Trained with Topological Features Learn Different Internal Representations?

Sarah McGuire, Shane Jackson, Tegan Emerson, Henry Kvinge

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments To appear at NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations (NeurReps)

2211.04198 2022-11-09 cs.CL 57%

Third-Party Aligner for Neural Word Alignments

Jinpeng Zhang, Chuanqi Dong, Xiangyu Duan, Yuqi Zhang, Min Zhang

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments 12 pages, 4 figures, findings of emnlp 2022

2209.12146 2022-11-09 eess.SY cs.LG cs.SY stat.ML 57%

Machine Learning and Artificial Intelligence-Driven Multi-Scale Modeling for High Burnup Accident-Tolerant Fuels for Light Water-Based SMR Applications

Md. Shamim Hassan, Abid Hossain Khan, Richa Verma, Dinesh Kumar, Kazuma Kobayashi, Shoaib Usman, Syed Alam

专题命中其他安全：safety(abstract)；分类 cs.LG

Journal ref Handbook of Smart Energy Systems, 2022

2211.00586 2022-11-02 cs.CL cs.SD eess.AS 57%

T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5

Chan-Jan Hsu, Ho-Lam Chung, Hung-yi Lee, Yu Tsao

专题命中其他安全：alignment(abstract)；分类 cs.CL

2210.14161 2022-10-26 cs.CV cs.AI 57%

Aligning MAGMA by Few-Shot Learning and Finetuning

Jean-Charles Layoun, Alexis Roger, Irina Rish

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments Accepted by the Montreal AI Symposium conference in 2022

2210.14070 2022-10-26 cs.LG 57%

Useful Confidence Measures: Beyond the Max Score

Gal Yona, Amir Feder, Itay Laish

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments Short paper; appeared in the Workshop on Distribution Shifts @ NeurIPS 2022

2205.12688 2022-10-26 cs.CL 57%

ProsocialDialog: A Prosocial Backbone for Conversational Agents

Hyunwoo Kim, Youngjae Yu, Liwei Jiang, Ximing Lu, Daniel Khashabi, Gunhee Kim, Yejin Choi, Maarten Sap

专题命中其他安全：safety(abstract)；分类 cs.CL

Comments EMNLP 2022 camera ready; Dataset and model can be found at https://hyunw.kim/prosocial-dialog/

2105.02276 2022-10-21 quant-ph cs.LG 57%

Training Quantum Embedding Kernels on Near-Term Quantum Computers

Thomas Hubregtsen, David Wierichs, Elies Gil-Fuster, Peter-Jan H. S. Derks, Paul K. Faehrmann, Johannes Jakob Meyer

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments 19 pages, 13 figures

Journal ref Phys. Rev. A 106, 042431 (2022)

2210.08879 2022-10-18 cs.RO cs.AI cs.HC 57%

Robust Planning for Human-Robot Joint Tasks with Explicit Reasoning on Human Mental State

Anthony Favier, Shashank Shekhar, Rachid Alami

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments 10 pages, 2 figures, 1 table, AI-HRI AAAI 2022 Fall Symposium Series

2206.06583 2022-10-18 q-bio.QM cs.AI 57%

Exploring evolution-aware & -free protein language models as protein function predictors

Mingyang Hu, Fajie Yuan, Kevin K. Yang, Fusong Ju, Jin Su, Hui Wang, Fei Yang, Qiuyang Ding

专题命中其他安全：alignment(abstract)；分类 cs.AI

2203.11635 2022-10-18 cs.LG 57%

Feature Distribution Matching for Federated Domain Generalization

Yuwei Sun, Ng Chong, Hideya Ochiai

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments Accepted for Asian Conference on Machine Learning (ACML 2022)

2210.06956 2022-10-14 cs.SE cs.AI 57%

On-Premise Artificial Intelligence as a Service for Small and Medium Size Setups

Carolina Fortuna, Din Mušić, Gregor Cerar, Andrej Čampa, Panagiotis Kapsalis, Mihael Mohorčič

专题命中其他安全：safety(abstract)；分类 cs.AI

Comments 11 Pages, 8 Figures, book chapter

2210.03941 2022-10-11 cs.CV cs.CL 57%

Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling

Hsin-Ying Lee, Hung-Ting Su, Bing-Chen Tsai, Tsung-Han Wu, Jia-Fong Yeh, Winston H. Hsu

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments BMVC 2022. Code is available at https://github.com/shinying/dest

1910.08635 2022-10-06 cs.LG cs.CR stat.ML 57%

Tree-based Intelligent Intrusion Detection System in Internet of Vehicles

Li Yang, Abdallah Moubayed, Ismail Hamieh, Abdallah Shami

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments Published in IEEE Global Communications Conference (GLOBECOM) 2019; Code is available at Github link: https://github.com/Western-OC2-Lab/Intrusion-Detection-System-Using-Machine-Learning

2210.00825 2022-10-04 cs.LG q-bio.GN 57%

Self-omics: A Self-supervised Learning Framework for Multi-omics Cancer Data

Sayed Hashim, Karthik Nandakumar, Mohammad Yaqub

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments Preprint of an article published in Pacific Symposium on Biocomputing $©$ 2022 World Scientific Publishing Co., Singapore, http://psb.stanford.edu/

2203.03183 2022-09-27 cs.AI 57%

Find a Way Forward: a Language-Guided Semantic Map Navigator

Zehao Wang, Mingxiao Li, Minye Wu, Marie-Francine Moens, Tinne Tuytelaars

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments content revised

2004.09705 2022-09-26 cs.RO cs.AI 57%

Explainable Goal-Driven Agents and Robots -- A Comprehensive Review

Fatai Sado, Chu Kiong Loo, Wei Shiung Liew, Matthias Kerzel, Stefan Wermter

专题命中其他安全：safety(abstract)；分类 cs.AI

2209.11102 2022-09-23 cs.CL 57%

Scope of Pre-trained Language Models for Detecting Conflicting Health Information

Joseph Gatto, Madhusudan Basak, Sarah M. Preum

专题命中其他安全：safety(abstract)；分类 cs.CL

2209.05731 2022-09-14 cs.AR cs.AI 57%

A Many-ported and Shared Memory Architecture for High-Performance ADAS SoCs

Hao Luan, Yu Yao, Chang Huang

专题命中其他安全：safety(abstract)；分类 cs.AI

2209.00421 2022-09-02 cs.LG cs.SE 57%

Review of the AMLAS Methodology for Application in Healthcare

Shakir Laher, Carla Brackstone, Sara Reis, An Nguyen, Sean White, Ibrahim Habli

专题命中其他安全：safety(abstract)；分类 cs.LG

2208.14426 2022-08-31 cs.AI cs.LO 57%

Correct-by-Construction Runtime Enforcement in AI -- A Survey

Bettina Könighofer, Roderick Bloem, Rüdiger Ehlers, Christian Pek

专题命中其他安全：safety(abstract)；分类 cs.AI

2208.08834 2022-08-19 eess.IV cs.LG 57%

Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis

Stefan Röhrl, Alice Hein, Lucie Huang, Dominik Heim, Christian Klenk, Manuel Lengl, Martin Knopp, Nawal Hafez, Oliver Hayden, Klaus Diepold

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments Presented at the 2nd Workshop on Interpretable Machine Learning in Healthcare (IMLH) @ ICML 2022

1. 其他安全 8095 篇

Improving the Cross-Lingual Generalisation in Visual Question Answering

Machine Learning for Smart and Energy-Efficient Buildings

Self-supervised vision-language pretraining for Medical visual question answering

RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN

Evaluating COVID-19 Sequence Data Using Nearest-Neighbors Based Network Model

Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile Robot

UDAAN: Machine Learning based Post-Editing tool for Document Translation

Handling Hard Affine SDP Shape Constraints in RKHSs

Do Neural Networks Trained with Topological Features Learn Different Internal Representations?

Third-Party Aligner for Neural Word Alignments

Machine Learning and Artificial Intelligence-Driven Multi-Scale Modeling for High Burnup Accident-Tolerant Fuels for Light Water-Based SMR Applications

T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5

Aligning MAGMA by Few-Shot Learning and Finetuning

Useful Confidence Measures: Beyond the Max Score

ProsocialDialog: A Prosocial Backbone for Conversational Agents

Training Quantum Embedding Kernels on Near-Term Quantum Computers

Robust Planning for Human-Robot Joint Tasks with Explicit Reasoning on Human Mental State

Exploring evolution-aware & -free protein language models as protein function predictors

Feature Distribution Matching for Federated Domain Generalization

On-Premise Artificial Intelligence as a Service for Small and Medium Size Setups

Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling

Tree-based Intelligent Intrusion Detection System in Internet of Vehicles

Self-omics: A Self-supervised Learning Framework for Multi-omics Cancer Data

Find a Way Forward: a Language-Guided Semantic Map Navigator

Explainable Goal-Driven Agents and Robots -- A Comprehensive Review

Scope of Pre-trained Language Models for Detecting Conflicting Health Information

A Many-ported and Shared Memory Architecture for High-Performance ADAS SoCs

Review of the AMLAS Methodology for Application in Healthcare

Correct-by-Construction Runtime Enforcement in AI -- A Survey

Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis