大模型对齐与安全 - arXivDaily 专题

2208.08629 2022-08-19 cs.CL 57%

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments COLING 2022

2208.08198 2022-08-18 cs.SE cs.LG 57%

Assurance Cases as Foundation Stone for Auditing AI-enabled and Autonomous Systems: Workshop Results and Political Recommendations for Action from the ExamAI Project

Rasmus Adler, Michael Klaes

专题命中其他安全：safety(abstract)；分类 cs.LG

2208.02865 2022-08-08 physics.ins-det cs.LG 57%

Towards Augmented Microscopy with Reinforcement Learning-Enhanced Workflows

Michael Xu, Abinash Kumar, James M. LeBeau

专题命中其他安全：alignment(abstract)；分类 cs.LG

2207.11769 2022-07-26 cs.LG 57%

CODiT: Conformal Out-of-Distribution Detection in Time-Series Data

Ramneet Kaur, Kaustubh Sridhar, Sangdon Park, Susmit Jha, Anirban Roy, Oleg Sokolsky, Insup Lee

专题命中其他安全：safety(abstract)；分类 cs.LG

2207.10149 2022-07-22 cs.SI cs.LG 57%

Digraphwave: Scalable Extraction of Structural Node Embeddings via Diffusion on Directed Graphs

Ciwan Ceylan, Kambiz Ghoorchian, Danica Kragic

专题命中其他安全：alignment(abstract)；分类 cs.LG

2204.08387 2022-07-20 cs.CL cs.CV 57%

LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking

Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments ACM Multimedia 2022

2206.03130 2022-07-14 cs.LG 57%

Towards Meta-learned Algorithm Selection using Implicit Fidelity Information

Aditya Mohan, Tim Ruhkopf, Marius Lindauer

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments Camera-ready version

2202.01671 2022-07-13 stat.ML cs.LG 57%

Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets

Tal Shnitzer, Mikhail Yurochkin, Kristjan Greenewald, Justin Solomon

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments 23 pages, 9 figures

2203.17090 2022-07-06 cs.CL 57%

PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model

Fei Mi, Yitong Li, Yulong Zeng, Jingyan Zhou, Yasheng Wang, Chuanfei Xu, Lifeng Shang, Xin Jiang, Shiqi Zhao, Qun Liu

专题命中其他安全：safety(abstract)；分类 cs.CL

Comments Update model and results; add comparison with EVA2.0

2207.00627 2022-07-05 cs.FL cs.CL 57%

Interactive Learning from Natural Language and Demonstrations using Signal Temporal Logic

Sara Mohammadinejad, Jesse Thomason, Jyotirmoy V. Deshmukh

专题命中其他安全：safety(abstract)；分类 cs.CL

2204.03409 2022-07-05 cs.CL cs.SD eess.AS 57%

MAESTRO: Matched Speech Text Representations through Modality Matching

Zhehuai Chen, Yu Zhang, Andrew Rosenberg, Bhuvana Ramabhadran, Pedro Moreno, Ankur Bapna, Heiga Zen

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments Accepted by Interspeech 2022

2207.00295 2022-07-04 cs.CY cs.CR 57%

The Dangers of Computational Law and Cybersecurity; Perspectives from Engineering and the AI Act

Kaspar Rosager Ludvigsen, Shishir Nagaraja, Angela Daly

专题命中其他安全：safety(abstract)；分类 cs.CY

Comments 17 pages, 1 figure

2206.15444 2022-07-01 cs.LG 57%

Learning Functions on Multiple Sets using Multi-Set Transformers

Kira Selby, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart

专题命中其他安全：alignment(abstract)；分类 cs.LG

2206.11831 2022-06-24 cs.AI 57%

On Avoiding Power-Seeking by Artificial Intelligence

Alexander Matt Turner

专题命中其他安全：alignment(abstract)；分类 cs.AI

Comments 287 pages, PhD thesis

2206.10544 2022-06-22 cs.RO cs.AI cs.SY eess.SY 57%

Multi-UAV Planning for Cooperative Wildfire Coverage and Tracking with Quality-of-Service Guarantees

Esmaeil Seraj, Andrew Silva, Matthew Gombolay

专题命中其他安全：safety(abstract)；分类 cs.AI

Comments To appear in the journal of Autonomous Agents and Multi-Agent Systems (AAMAS)

2206.09603 2022-06-22 cs.RO cs.LG 57%

Constrained Reinforcement Learning for Robotics via Scenario-Based Programming

Davide Corsi, Raz Yerushalmi, Guy Amir, Alessandro Farinelli, David Harel, Guy Katz

专题命中其他安全：safety(abstract)；分类 cs.LG

1802.07024 2022-06-22 stat.ML cs.LG 57%

A General Framework for Abstention Under Label Shift

Amr M. Alexandari, Anshul Kundaje, Avanti Shrikumar

专题命中其他安全：safety(abstract)；分类 cs.LG

2206.09074 2022-06-22 cs.LG eess.SP 57%

Weakly Supervised Classification of Vital Sign Alerts as Real or Artifact

Arnab Dey, Mononito Goswami, Joo Heung Yoon, Gilles Clermont, Michael Pinsky, Marilyn Hravnak, Artur Dubrawski

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments Accepted at American Medical Informatics Association (AMIA) Annual Symposium 2022. 10 pages, 4 figures and 2 tables

2206.08723 2022-06-20 cs.CL 57%

CookDial: A dataset for task-oriented dialogs grounded in procedural documents

Yiwei Jiang, Klim Zaporojets, Johannes Deleu, Thomas Demeester, Chris Develder

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments The dataset and codes are available at https://github.com/YiweiJiang2015/CookDial

Journal ref Applied Intelligence, 1-19 (2022)

2206.07403 2022-06-16 cs.MA cs.LG 57%

Automating the resolution of flight conflicts: Deep reinforcement learning in service of air traffic controllers

George Vouros, George Papadopoulos, Alevizos Bastas, Jose Manuel Cordero, Ruben Rodrigez Rodrigez

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments 20 pages, 5 figures, 3 tables

2106.15986 2022-06-01 cs.CL 57%

Cross-lingual alignments of ELMo contextual embeddings

Matej Ulčar, Marko Robnik-Šikonja

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments 30 pages, 5 figures

Journal ref Neural Computing and Applications, 2022

2201.06274 2022-05-31 cs.AI cs.MA math.CO math.GT math.MG 57%

Detecting danger in gridworlds using Gromov's Link Condition

Thomas F Burns, Robert Tang

专题命中其他安全：safety(abstract)；分类 cs.AI

Comments 17 pages, 12 figures, 4 appendices; some parts rewritten and rearranged to improve exposition, no changes to mathematical content

2106.02081 2022-05-31 stat.ML cs.LG 57%

Solving Schrödinger Bridges via Maximum Likelihood

Francisco Vargas, Pierre Thodoroff, Neil D. Lawrence, Austen Lamacraft

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments 9 pages + appendix (total 28 pages)

Journal ref Entropy. 2021; 23(9):1134

2205.11191 2022-05-26 cs.CV cs.AI 57%

NPU-BOLT: A Dataset for Bolt Object Detection in Natural Scene Images

Yadian Zhao, Zhenglin Yang, Chao Xu

专题命中其他安全：safety(abstract)；分类 cs.AI

2205.11469 2022-05-24 cs.LG cs.SY eess.SY 57%

Advanced Transient Diagnostic with Ensemble Digital Twin Modeling

Edward Chen, Linyu Lin, Nam T. Dinh

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments 9 pages, 4 figures, 3 tables, presented in the American Nuclear Society Mathematics and Computation 2021 Annual Conference

2204.07441 2022-05-23 cs.CV cs.CL cs.IR 57%

COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

Haoyu Lu, Nanyi Fei, Yuqi Huo, Yizhao Gao, Zhiwu Lu, Ji-Rong Wen

专题命中其他安全：alignment(abstract)；分类 cs.CL

Comments Accepted by CVPR2022

2205.06907 2022-05-17 cs.LG 57%

Multimodal Conversational AI: A Survey of Datasets and Approaches

Anirudh Sundar, Larry Heck

专题命中其他安全：alignment(abstract)；分类 cs.LG

Comments 17 pages, 1 figure, to be published in the 4th Workshop on NLP for Conversational AI

2205.04044 2022-05-16 eess.IV cs.CV cs.LG 57%

Masked Co-attentional Transformer reconstructs 100x ultra-fast/low-dose whole-body PET from longitudinal images and anatomically guided MRI

Yan-Ran, Wang, Liangqiong Qu, Natasha Diba Sheybani, Xiaolong Luo, Jiangshan Wang, Kristina Elizabeth Hawk, Ashok Joseph Theruvath, Sergios Gatidis, Xuerong Xiao, Allison Pribnow, Daniel Rubin, Heike E. Daldrup-Link

专题命中其他安全：safety(abstract)；分类 cs.LG

Comments This submission has been removed by arXiv administrators because the submitter did not have the right to assign the license at the time of submission

2205.05488 2022-05-12 cs.ET cs.IT cs.LG math.IT 57%

DNA data storage, sequencing data-carrying DNA

Jasmine Quah, Omer Sella, Thomas Heinis

专题命中其他安全：alignment(abstract)；分类 cs.LG

2205.01076 2022-05-03 cs.LG 57%

Classification of Buildings' Potential for Seismic Damage by Means of Artificial Intelligence Techniques

Konstantinos Kostinakis, Konstantinos Morfidis, Konstantinos Demertzis, Lazaros Iliadis

专题命中其他安全：safety(abstract)；分类 cs.LG

1. 其他安全 8095 篇

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

Assurance Cases as Foundation Stone for Auditing AI-enabled and Autonomous Systems: Workshop Results and Political Recommendations for Action from the ExamAI Project

Towards Augmented Microscopy with Reinforcement Learning-Enhanced Workflows

CODiT: Conformal Out-of-Distribution Detection in Time-Series Data

Digraphwave: Scalable Extraction of Structural Node Embeddings via Diffusion on Directed Graphs

LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking

Towards Meta-learned Algorithm Selection using Implicit Fidelity Information

Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets

PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model

Interactive Learning from Natural Language and Demonstrations using Signal Temporal Logic

MAESTRO: Matched Speech Text Representations through Modality Matching

The Dangers of Computational Law and Cybersecurity; Perspectives from Engineering and the AI Act

Learning Functions on Multiple Sets using Multi-Set Transformers

On Avoiding Power-Seeking by Artificial Intelligence

Multi-UAV Planning for Cooperative Wildfire Coverage and Tracking with Quality-of-Service Guarantees

Constrained Reinforcement Learning for Robotics via Scenario-Based Programming

A General Framework for Abstention Under Label Shift

Weakly Supervised Classification of Vital Sign Alerts as Real or Artifact

CookDial: A dataset for task-oriented dialogs grounded in procedural documents

Automating the resolution of flight conflicts: Deep reinforcement learning in service of air traffic controllers

Cross-lingual alignments of ELMo contextual embeddings

Detecting danger in gridworlds using Gromov's Link Condition

Solving Schrödinger Bridges via Maximum Likelihood

NPU-BOLT: A Dataset for Bolt Object Detection in Natural Scene Images

Advanced Transient Diagnostic with Ensemble Digital Twin Modeling

COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

Multimodal Conversational AI: A Survey of Datasets and Approaches

Masked Co-attentional Transformer reconstructs 100x ultra-fast/low-dose whole-body PET from longitudinal images and anatomically guided MRI

DNA data storage, sequencing data-carrying DNA

Classification of Buildings' Potential for Seismic Damage by Means of Artificial Intelligence Techniques