大模型对齐与安全

Emergence of Scale-Free Networks in Social Interactions among Large Language Models

Giordano De Marzo, Luciano Pietronero, David Garcia

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

Enhancing Situational Awareness in Surveillance: Leveraging Data Visualization Techniques for Machine Learning-based Video Analytics Outcomes

Babak Rahimi Ardabili, Shanle Yao, Armin Danesh Pazho, Lauren Bourque, Hamed Tabkhi

专题命中 其他安全 ：safety(abstract)；分类 cs.CY

Comments 15 pages, 8 figures

Autonomous Advanced Aerial Mobility -- An End-to-end Autonomy Framework for UAVs and Beyond

Sakshi Mishra, Praveen Palanisamy

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 33 pages, 12 figures

Personality of AI

Byunggu Yu, Junwhan Kim

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

Deep Set Neural Networks for forecasting asynchronous bioprocess timeseries

Maxim Borisyak, Stefan Born, Peter Neubauer, Mariano Nicolas Cruz-Bournazou

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

Comments 9 pages, 3 figures

AutoRepo: A general framework for multi-modal LLM-based automated construction reporting

Hongxu Pu, Xincong Yang, Jing Li, Runhao Guo, Heng Li

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments We believe that keeping this version of the paper publicly available may lead to confusion or misinterpretation regarding our current research direction and findings

Diffeomorphic Learning

Laurent Younes

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

Journal ref Journal of Machine Learning Research: 21(220):1-28, 2020

Linear normalised hash function for clustering gene sequences and identifying reference sequences from multiple sequence alignments

Manal Helal, Fanrong Kong, Sharon C-A Chen, Fei Zhou, Dominic E Dwyer, John Potter, Vitali Sintchenko

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

Journal ref Microbial Informatics and Experimentation volume 2, Article number: 2 (2012) https://microbialinformaticsj.biomedcentral.com/counter/pdf/10.1186/2042-5783-2-2.pdf

Counter-terrorism in cyber-physical spaces: Best practices and technologies from the state of the art

Giuseppe Cascavilla, Damian A. Tamburri, Francesco Leotta, Massimo Mecella, WillemJan Van Den Heuvel

专题命中 其他安全 ：safety(abstract)；分类 cs.CY

Journal ref Information and Software Technology, Volume 161, 2023, 107260, ISSN 0950-5849

SemanticBoost: Elevating Motion Generation with Augmented Textual Cues

Xin He, Shaoli Huang, Xiaohang Zhan, Chao Weng, Ying Shan

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

FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax

Yu Lu, Linchao Zhu, Hehe Fan, Yi Yang

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

Comments Project page: https://flowzero-video.github.io

HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning

Yongjin Yang, Joonkee Kim, Yujin Kim, Namgyu Ho, James Thorne, Se-young Yun

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Comments Findings of EMNLP 2023; The first three authors contribute equally

Perceptual Structure in the Absence of Grounding for LLMs: The Impact of Abstractedness and Subjectivity in Color Language

Pablo Loyola, Edison Marrese-Taylor, Andres Hoyos-Idobro

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

Comments EMNLP 2023 Findings

Echocardiogram Foundation Model -- Application 1: Estimating Ejection Fraction

Adil Dahlan, Cyril Zakka, Abhinav Kumar, Laura Tang, Rohan Shad, Robyn Fong, William Hiesinger

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model

Simon K. S. Chu, Kathy Y. Wei

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

On Functional Activations in Deep Neural Networks

Andrew S. Nencka, L. Tugan Muftuler, Peter LaViolette, Kevin M. Koch

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

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

Ethan Pronovost, Meghana Reddy Ganesina, Noureldin Hendy, Zeyu Wang, Andres Morales, Kai Wang, Nicholas Roy

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments NeurIPS 2023

Automatic Generation of Scenarios for System-level Simulation-based Verification of Autonomous Driving Systems

Srajan Goyal, Alberto Griggio, Jacob Kimblad, Stefano Tonetta

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments In Proceedings FMAS 2023, arXiv:2311.08987

Journal ref EPTCS 395, 2023, pp. 113-129

Smart Home Goal Feature Model -- A guide to support Smart Homes for Ageing in Place

Irini Logothetis, Priya Rani, Shangeetha Sivasothy, Rajesh Vasa, Kon Mouzakis

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments Preprint 9 pages

VegaEdge: Edge AI Confluence Anomaly Detection for Real-Time Highway IoT-Applications

Vinit Katariya, Fatema-E- Jannat, Armin Danesh Pazho, Ghazal Alinezhad Noghre, Hamed Tabkhi

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Intentional Biases in LLM Responses

Nicklaus Badyal, Derek Jacoby, Yvonne Coady

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

Anomaly Detection in Industrial Machinery using IoT Devices and Machine Learning: a Systematic Mapping

Sérgio F. Chevtchenko, Elisson da Silva Rocha, Monalisa Cristina Moura Dos Santos, Ricardo Lins Mota, Diego Moura Vieira, Ermeson Carneiro de Andrade, Danilo Ricardo Barbosa de Araújo

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Model-as-a-Service (MaaS): A Survey

Wensheng Gan, Shicheng Wan, Philip S. Yu

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

Comments Preprint. 3 figures, 1 tables

Joint processing of linguistic properties in brains and language models

Subba Reddy Oota, Manish Gupta, Mariya Toneva

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

Comments 22 pages, 12 figures, To be published in the proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, USA

Do Language Models Learn Semantics of Code? A Case Study in Vulnerability Detection

Benjamin Steenhoek, Md Mahbubur Rahman, Shaila Sharmin, Wei Le

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

Staged Reinforcement Learning for Complex Tasks through Decomposed Environments

Rafael Pina, Corentin Artaud, Xiaolan Liu, Varuna De Silva

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Intelligent Systems and Pattern Recognition 2023 (ISPR 2023)

Neurosymbolic AI -- Why, What, and How

Amit Sheth, Kaushik Roy, Manas Gaur

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments To appear in IEEE Intelligent Systems

A Robust Backpropagation-Free Framework for Images

Timothy Zee, Alexander G. Ororbia, Ankur Mali, Ifeoma Nwogu

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

CoinRun: Solving Goal Misgeneralisation

Stuart Armstrong, Alexandre Maranhão, Oliver Daniels-Koch, Patrick Leask, Rebecca Gorman

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

The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer

Pavel Efimov, Leonid Boytsov, Elena Arslanova, Pavel Braslavski

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

Comments Presented at ECIR 2023