大模型对齐与安全

Synergistic Signal Denoising for Multimodal Time Series of Structure Vibration

Yang Yu, Han Chen

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Machine Learning for QoS Prediction in Vehicular Communication: Challenges and Solution Approaches

Alexandros Palaios, Christian L. Vielhaus, Daniel F. Külzer, Cara Watermann, Rodrigo Hernangomez, Sanket Partani, Philipp Geuer, Anton Krause, Raja Sattiraju, Martin Kasparick, Gerhard Fettweis, Frank H. P. Fitzek, Hans D. Schotten, Slawomir Stanczak

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 18 pages, 12 Figures. Accepted on IEEE Access

Introducing Hybrid Modeling with Time-series-Transformers: A Comparative Study of Series and Parallel Approach in Batch Crystallization

Niranjan Sitapure, Joseph S Kwon

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 20 pages, 9 figures. Submitted as preprint to Industrial & Engineering Chemistry Research Journal

VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts

Longtian Qiu, Renrui Zhang, Ziyu Guo, Ziyao Zeng, Zilu Guo, Yafeng Li, Guangnan Zhang

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

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

Ruixiang Jiang, Lingbo Liu, Changwen Chen

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

Comments Accepted by ACM MM 2023

A data-driven approach to predict decision point choice during normal and evacuation wayfinding in multi-story buildings

Yan Feng, Panchamy Krishnakumari

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Facilitating Sim-to-real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulation

Ram Dershan, Amir M. Soufi Enayati, Zengjie Zhang, Dean Richert, Homayoun Najjaran

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis

Ziao Wang, Yuhang Li, Junda Wu, Jaehyeon Soon, Xiaofeng Zhang

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

Comments (FinLLM 2023)@IJCAI 2023

SurveyLM: A platform to explore emerging value perspectives in augmented language models' behaviors

Steve J. Bickley, Ho Fai Chan, Bang Dao, Benno Torgler, Son Tran

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

Comments 8 pages, 1 figure

A Comparative Analysis of Machine Learning Methods for Lane Change Intention Recognition Using Vehicle Trajectory Data

Renteng Yuan

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments arXiv admin note: text overlap with arXiv:2304.13732

Detection of Children Abuse by Voice and Audio Classification by Short-Time Fourier Transform Machine Learning implemented on Nvidia Edge GPU device

Jiuqi Yan, Yingxian Chen, W. W. T. Fok

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 5 pages, 7 figures, PRAI 2023

Emotional Intelligence of Large Language Models

Xuena Wang, Xueting Li, Zi Yin, Yue Wu, Liu Jia

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

Comments 36 pages, 5 figures

ARC-NLP at PAN 2023: Hierarchical Long Text Classification for Trigger Detection

Umitcan Sahin, Izzet Emre Kucukkaya, Cagri Toraman

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Comments Accepted by PAN at CLEF 2023

A Strategic Framework for Optimal Decisions in Football 1-vs-1 Shot-Taking Situations: An Integrated Approach of Machine Learning, Theory-Based Modeling, and Game Theory

Calvin C. K. Yeung, Keisuke Fujii

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

Bug Characterization in Machine Learning-based Systems

Mohammad Mehdi Morovati, Amin Nikanjam, Florian Tambon, Foutse Khomh, Zhen Ming, Jiang

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Towards exploring adversarial learning for anomaly detection in complex driving scenes

Nour Habib, Yunsu Cho, Abhishek Buragohain, Andreas Rausch

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments 22

Explaining Autonomous Driving Actions with Visual Question Answering

Shahin Atakishiyev, Mohammad Salameh, Housam Babiker, Randy Goebel

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments Accepted to the 2023 IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC-2023)

Revisiting invariances and introducing priors in Gromov-Wasserstein distances

Pinar Demetci, Quang Huy Tran, Ievgen Redko, Ritambhara Singh

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

Enhancing Evacuation Planning through Multi-Agent Simulation and Artificial Intelligence: Understanding Human Behavior in Hazardous Environments

Afnan Alazbah, Khalid Fakeeh, Osama Rabie

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments 21 pages,15 figures

ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts

Minghao Xu, Xinyu Yuan, Santiago Miret, Jian Tang

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

Comments Accpeted by ICML 2023 (Oral), code and data released

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, Hehong Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

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

Journal ref EMNLP2022

Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models

Yong Cheng, Yu Zhang, Melvin Johnson, Wolfgang Macherey, Ankur Bapna

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

Comments ICML 2023

Exploring Qualitative Research Using LLMs

Muneera Bano, Didar Zowghi, Jon Whittle

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

Bioinformatics and Classical Literary Study

Pramit Chaudhuri, Joseph P. Dexter

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

Journal ref Journal of Data Mining & Digital Humanities, Special Issue on Computer-Aided Processing of Intertextuality in Ancient Languages, Project presentations (August 19, 2017) jdmdh:1386

Validation of artificial intelligence containing products across the regulated healthcare industries

David Higgins, Christian Johner

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

Comments 33 pages, 3 figures, 1 table. A version of this preprint with messy formatting is available from https://www.researchsquare.com/article/rs-2153749/v1

Journal ref Ther Innov Regul Sci 57, 797-809 (2023)

Knowledge-Prompted Estimator: A Novel Approach to Explainable Machine Translation Assessment

Hao Yang, Min Zhang, Shimin Tao, Minghan Wang, Daimeng Wei, Yanfei Jiang

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

Closing the Loop: Testing ChatGPT to Generate Model Explanations to Improve Human Labelling of Sponsored Content on Social Media

Thales Bertaglia, Stefan Huber, Catalina Goanta, Gerasimos Spanakis, Adriana Iamnitchi

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

Comments Accepted to The World Conference on eXplainable Artificial Intelligence, Lisbon, Portugal, July 2023

M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning

Lei Li, Yuwei Yin, Shicheng Li, Liang Chen, Peiyi Wang, Shuhuai Ren, Mukai Li, Yazheng Yang, Jingjing Xu, Xu Sun, Lingpeng Kong, Qi Liu

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

Comments Fix dataset url: https://huggingface.co/datasets/MMInstruction/M3IT Project: https://m3-it.github.io/

Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit

Xinhang Li, Yiying Yang, Zheng Yuan, Zhe Wang, Qinwen Wang, Chen Xu, Lei Li, Jianhua He, Lin Zhang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Neural Embeddings for Protein Graphs

Francesco Ceccarelli, Lorenzo Giusti, Sean B. Holden, Pietro Liò

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

Comments 10 pages, 5 figures