大模型对齐与安全 - arXivDaily 专题

2305.05940 2023-06-27 cs.CL 79%

Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment

Eshaan Tanwar, Subhabrata Dutta, Manish Borthakur, Tanmoy Chakraborty

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

Comments Accepted in ACL 2023. Code available at https://github.com/EshaanT/X-InSTA

2306.02871 2023-06-06 cs.CL 79%

Text-To-KG Alignment: Comparing Current Methods on Classification Tasks

Sondre Wold, Lilja Øvrelid, Erik Velldal

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

Comments Camera ready version for MATCHING workshop at ACL 2023

2306.01824 2023-06-06 q-bio.QM cs.CE cs.LG q-bio.BM 79%

Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation

Le Zhang, Jiayang Chen, Tao Shen, Yu Li, Siqi Sun

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

2305.19747 2023-06-01 cs.CL 79%

Analyzing Text Representations by Measuring Task Alignment

Cesar Gonzalez-Gutierrez, Audi Primadhanty, Francesco Cazzaro, Ariadna Quattoni

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

Comments arXiv admin note: text overlap with arXiv:2210.05721

2305.11501 2023-05-22 cs.CL 79%

From Alignment to Entailment: A Unified Textual Entailment Framework for Entity Alignment

Yu Zhao, Yike Wu, Xiangrui Cai, Ying Zhang, Haiwei Zhang, Xiaojie Yuan

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

Comments Accepted by ACL 2023 Findings

2305.07366 2023-05-15 cs.MA cs.AI cs.NE 79%

Multi-Value Alignment in Normative Multi-Agent System: Evolutionary Optimisation Approach

Maha Riad, Vinicius Renan de Carvalho, Fatemeh Golpayegani

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

2303.01926 2023-04-20 cs.LG 79%

RAFEN -- Regularized Alignment Framework for Embeddings of Nodes

Kamil Tagowski, Piotr Bielak, Jakub Binkowski, Tomasz Kajdanowicz

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

Comments ICCS 2023

2304.07611 2023-04-18 cs.CL eess.AS 79%

A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition

Ruchao Fan, Wei Chu, Peng Chang, Abeer Alwan

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

Comments Published in IEEE Transactions on Audio, Speech, and Language Processing

2212.10898 2023-03-02 cs.CL q-bio.NC 79%

Training language models to summarize narratives improves brain alignment

Khai Loong Aw, Mariya Toneva

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

Comments ICLR 2023 (notable top 25%)

2106.06237 2023-02-21 eess.IV cs.CV cs.LG 79%

KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation

Chenhong Zhou, Feng Liu, Chen Gong, Rongfei Zeng, Tongliang Liu, William K. Cheung, Bo Han

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

Comments 18 pages

Journal ref Transactions on Machine Learning Research, 2023

2301.07174 2023-01-19 cs.CV cs.LG cs.RO 79%

Creating awareness about security and safety on highways to mitigate wildlife-vehicle collisions by detecting and recognizing wildlife fences using deep learning and drone technology

Irene Nandutu, Marcellin Atemkeng, Patrice Okouma, Nokubonga Mgqatsa, Jean Louis Ebongue Kedieng Fendji, Franklin Tchakounte

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

2301.01038 2023-01-04 cs.LG 79%

Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS)

Natalie Gentner, Gian Antonio Susto

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

2212.01810 2022-12-06 cs.CL 79%

Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Fei Mi, Yasheng Wang, Lifeng Shang, Minlie Huang

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

Comments Findings of EMNLP 2022

2111.06862 2022-11-30 cs.LG physics.app-ph physics.optics 79%

Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment

Matthew J. Filipovich, Zhimu Guo, Mohammed Al-Qadasi, Bicky A. Marquez, Hugh D. Morison, Volker J. Sorger, Paul R. Prucnal, Sudip Shekhar, Bhavin J. Shastri

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

Comments 15 pages, 6 figures

Journal ref Optica 9, 1323-1332 (2022)

2210.12774 2022-11-01 stat.ML cs.LG 79%

Manifold Alignment with Label Information

Andres F. Duque, Myriam Lizotte, Guy Wolf, Kevin R. Moon

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

2210.15000 2022-10-28 cs.LG cs.CV 79%

Trade-off between reconstruction loss and feature alignment for domain generalization

Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron

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

Comments 13 pages, 2 tables

Journal ref International Conference on Machine Learning and Applications (ICMLA-2022)

2104.08721 2022-10-12 cs.CL 79%

Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry

Kelly Marchisio, Conghao Xiong, Philipp Koehn

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

Comments AMTA2022 Camera Ready

2210.04141 2022-10-11 cs.CL 79%

Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment

Siyu Lai, Zhen Yang, Fandong Meng, Yufeng Chen, Jinan Xu, Jie Zhou

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

Comments Accepted by EMNLP 2022

2208.13628 2022-10-06 cs.CV cs.LG 79%

Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment

Mustafa Shukor, Guillaume Couairon, Matthieu Cord

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

Comments BMVC 2022

2210.00095 2022-10-04 cs.SE cs.AI cs.MA 79%

Safety-Critical Adaptation in Self-Adaptive Systems

Simon Diemert, Jens H. Weber

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

Comments Submitted to The 1st IEEE International Workshop on Assured Autonomy, Artificial Intelligence and Machine Learning (WAAM) 2022

2209.11842 2022-09-27 cs.CL cs.HC cs.RO 79%

Comparison of Lexical Alignment with a Teachable Robot in Human-Robot and Human-Human-Robot Interactions

Yuya Asano, Diane Litman, Mingzhi Yu, Nikki Lobczowski, Timothy Nokes-Malach, Adriana Kovashka, Erin Walker

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

Comments To be published in SIGDial 2022

2201.12596 2022-09-15 cs.CV cs.AI cs.MM 79%

MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning

Zejun Li, Zhihao Fan, Huaixiao Tou, Jingjing Chen, Zhongyu Wei, Xuanjing Huang

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

Comments Accepted by ACM MM22

2202.12846 2022-08-17 cs.LG 79%

An initial alignment between neural network and target is needed for gradient descent to learn

Emmanuel Abbe, Elisabetta Cornacchia, Jan Hązła, Christopher Marquis

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

Journal ref Proceedings of the International Conference on Machine Learning, 2022

2005.10242 2022-08-17 cs.LG cs.CV stat.ML 79%

Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere

Tongzhou Wang, Phillip Isola

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

Comments International Conference on Machine Learning (ICML), 2020

2201.05451 2022-08-10 cs.SE cs.LG cs.RO 79%

A causal model of safety assurance for machine learning

Simon Burton

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

2207.14174 2022-07-29 eess.SP cs.AI 79%

Bayesian Optimization-Based Beam Alignment for MmWave MIMO Communication Systems

Songjie Yang, Baojuan Liu, Zhiqin Hong, Zhongpei Zhang

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

2206.07305 2022-06-16 stat.ML cs.LG 79%

Diffusion Transport Alignment

Andres F. Duque, Guy Wolf, Kevin R. Moon

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

2205.08404 2022-05-18 cs.AI cs.NI 79%

A Comprehensive Study on Artificial Intelligence Algorithms to Implement Safety Using Communication Technologies

Rafia Inam, Alberto Yukinobu Hata, Vlasjov Prifti, Sara Abbaspour Asadollah

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

2204.10461 2022-04-25 cs.CL cs.SD eess.AS 79%

WaBERT: A Low-resource End-to-end Model for Spoken Language Understanding and Speech-to-BERT Alignment

Lin Yao, Jianfei Song, Ruizhuo Xu, Yingfang Yang, Zijian Chen, Yafeng Deng

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

2104.07642 2022-03-17 cs.CL 79%

Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining

Chih-chan Tien, Shane Steinert-Threlkeld

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

Comments To be published at ACL 2022. 11 pages, 2 figures

1. 其他安全 8017 篇

Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment

Text-To-KG Alignment: Comparing Current Methods on Classification Tasks

Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation

Analyzing Text Representations by Measuring Task Alignment

From Alignment to Entailment: A Unified Textual Entailment Framework for Entity Alignment

Multi-Value Alignment in Normative Multi-Agent System: Evolutionary Optimisation Approach

RAFEN -- Regularized Alignment Framework for Embeddings of Nodes

A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition

Training language models to summarize narratives improves brain alignment

KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation

Creating awareness about security and safety on highways to mitigate wildlife-vehicle collisions by detecting and recognizing wildlife fences using deep learning and drone technology

Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS)

Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment

Manifold Alignment with Label Information

Trade-off between reconstruction loss and feature alignment for domain generalization

Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry

Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment

Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment

Safety-Critical Adaptation in Self-Adaptive Systems

Comparison of Lexical Alignment with a Teachable Robot in Human-Robot and Human-Human-Robot Interactions

MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning

An initial alignment between neural network and target is needed for gradient descent to learn

Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere

A causal model of safety assurance for machine learning

Bayesian Optimization-Based Beam Alignment for MmWave MIMO Communication Systems

Diffusion Transport Alignment

A Comprehensive Study on Artificial Intelligence Algorithms to Implement Safety Using Communication Technologies

WaBERT: A Low-resource End-to-end Model for Spoken Language Understanding and Speech-to-BERT Alignment

Bilingual alignment transfers to multilingual alignment for unsupervised parallel text mining