大模型对齐与安全

Extend and Explain: Interpreting Very Long Language Models

Joel Stremmel, Brian L. Hill, Jeffrey Hertzberg, Jaime Murillo, Llewelyn Allotey, Eran Halperin

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CL

Comments 11 pages

Journal ref Proceedings of the 2nd Machine Learning for Health symposium, PMLR 193:218-258, 2022

Quantifying probabilistic robustness of tree-based classifiers against natural distortions

Christoph Schweimer, Sebastian Scher

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Comments 9 pages, 5 figures

A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics

Dimitris Panagopoulos, Giannis Petousakis, Aniketh Ramesh, Tianshu Ruan, Grigoris Nikolaou, Rustam Stolkin, Manolis Chiou

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments 6 pages, 4 figures, ICHMS 2022, First two Authors contributed equally

Active Inference and Behavior Trees for Reactive Action Planning and Execution in Robotics

Corrado Pezzato, Carlos Hernandez Corbato, Stefan Bonhof, Martijn Wisse

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Comments Accepted at Transactions on Robotics (IEEE T-RO)

PreMa: Predictive Maintenance of Solenoid Valve in Real-Time at Embedded Edge-Level

Prajwal BN, Harsha Yelchuri, Vishwanath Shastry, T. V. Prabhakar

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Doctors vs. Nurses: Understanding the Great Divide in Vaccine Hesitancy among Healthcare Workers

Sajid Hussain Rafi Ahamed, Shahid Shakil, Hanjia Lyu, Xinping Zhang, Jiebo Luo

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CY

Comments Accepted for publication in Proceedings of the 8th Special Session on Intelligent Data Mining of 2022 IEEE International Conference on Big Data, 2022

Technical Report on Neural Language Models and Few-Shot Learning for Systematic Requirements Processing in MDSE

Vincent Bertram, Miriam Boß, Evgeny Kusmenko, Imke Helene Nachmann, Bernhard Rumpe, Danilo Trotta, Louis Wachtmeister

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Robust Longitudinal Control for Vehicular Autonomous Platoons Using Deep Reinforcement Learning

Armando Alves Neto, Leonardo Amaral Mozelli

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

A Fine-grained Interpretability Evaluation Benchmark for Neural NLP

Lijie Wang, Yaozong Shen, Shuyuan Peng, Shuai Zhang, Xinyan Xiao, Hao Liu, Hongxuan Tang, Ying Chen, Hua Wu, Haifeng Wang

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CL

Journal ref CoNLL 2022

NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning

Buyun Liang, Tim Mitchell, Ju Sun

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Comments Accepted by the NeurIPS Workshop on Optimization for Machine Learning (OPT 2022). arXiv admin note: text overlap with arXiv:2111.13984

Physical Computing for Materials Acceleration Platforms

Erik Peterson, Alexander Lavin

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI

Journal ref MATTER, VOLUME 5, ISSUE 11, P3586-3596, NOVEMBER 02, 2022

Issues and Challenges in Applications of Artificial Intelligence to Nuclear Medicine -- The Bethesda Report (AI Summit 2022)

Arman Rahmim, Tyler J. Bradshaw, Irène Buvat, Joyita Dutta, Abhinav K. Jha, Paul E. Kinahan, Quanzheng Li, Chi Liu, Melissa D. McCradden, Babak Saboury, Eliot Siegel, John J. Sunderland, Richard L. Wahl

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.AI

UPainting: Unified Text-to-Image Diffusion Generation with Cross-modal Guidance

Wei Li, Xue Xu, Xinyan Xiao, Jiachen Liu, Hu Yang, Guohao Li, Zhanpeng Wang, Zhifan Feng, Qiaoqiao She, Yajuan Lyu, Hua Wu

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments First Version, 16 pages

Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model

Mingqi Li, Fei Ding, Dan Zhang, Long Cheng, Hongxin Hu, Feng Luo

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments accepted at EMNLP 2022

Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals

Rohin Shah, Vikrant Varma, Ramana Kumar, Mary Phuong, Victoria Krakovna, Jonathan Uesato, Zac Kenton

专题命中 安全评测 ：alignment(abstract)；分类 cs.LG

Behavior Trees in Robotics and AI: An Introduction

Michele Colledanchise, Petter Ögren

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Journal ref Chapman & Hall/CRC Artificial Intelligence and Robotics Series 2018

PHEE: A Dataset for Pharmacovigilance Event Extraction from Text

Zhaoyue Sun, Jiazheng Li, Gabriele Pergola, Byron C. Wallace, Bino John, Nigel Greene, Joseph Kim, Yulan He

专题命中 安全评测 ：safety(abstract)；分类 cs.CL

Comments 17 pages, 3 figures, EMNLP2022 accepted

Explainability in autonomous pedagogically structured scenarios

Minal Suresh Patil

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.AI

Comments Explainable Agency in Artificial Intelligence Workshop - 36th AAAI Conference on Artificial Intelligence

Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages

Idris Abdulmumin, Michael Beukman, Jesujoba O. Alabi, Chris Emezue, Everlyn Asiko, Tosin Adewumi, Shamsuddeen Hassan Muhammad, Mofetoluwa Adeyemi, Oreen Yousuf, Sahib Singh, Tajuddeen Rabiu Gwadabe

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments Accepted at the Seventh Conference on Machine Translation (WMT22)

Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task

Zhiwei He, Xing Wang, Zhaopeng Tu, Shuming Shi, Rui Wang

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

Comments WMT 2022

Application-Driven AI Paradigm for Hand-Held Action Detection

Kohou Wang, Zhaoxiang Liu, Shiguo Lian

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Neuro-symbolic Explainable Artificial Intelligence Twin for Zero-touch IoE in Wireless Network

Md. Shirajum Munir, Ki Tae Kim, Apurba Adhikary, Walid Saad, Sachin Shetty, Seong-Bae Park, Choong Seon Hong

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.AI

Comments Submitted to a journal for peer review

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent

Ruqi Zhang, Qiang Liu, Xin T. Tong

专题命中 安全评测 ：safety(abstract)；分类 cs.LG

Comments NeurIPS 2022

Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective

Mark Huasong Meng, Guangdong Bai, Sin Gee Teo, Zhe Hou, Yan Xiao, Yun Lin, Jin Song Dong

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Towards Semi-automatic Detection and Localization of Indoor Accessibility Issues using Mobile Depth Scanning and Computer Vision

Xia Su, Kaiming Cheng, Han Zhang, Jaewook Lee, Jon E. Froehlich

专题命中 安全评测 ：safety(abstract)；分类 cs.CY

Comments Workshop paper presented at "The 1st ASSETS'22 Workshop on The Future or urban Accessibility (UrbanAccess'22)"

Empowering the trustworthiness of ML-based critical systems through engineering activities

Juliette Mattioli, Agnes Delaborde, Souhaiel Khalfaoui, Freddy Lecue, Henri Sohier, Frederic Jurie

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.LG

Comments This work has been supported by the French government under the "France 2030" program, as part of the SystemX Technological Research Institute Research Institute

Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning

Cheng Liu, Erik-Jan van Kampen, Guido C. H. E. de Croon

专题命中 安全评测 ：safety(abstract)；分类 cs.AI

Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding

Changtong Zan, Liang Ding, Li Shen, Yu Cao, Weifeng Liu, Dacheng Tao

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL

FLAME: Federated Learning Across Multi-device Environments

Hyunsung Cho, Akhil Mathur, Fahim Kawsar

专题命中 安全评测 ：alignment(abstract)；分类 cs.LG

Journal ref Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 6, 3, Article 107 (September 2022)

Documenting use cases in the affective computing domain using Unified Modeling Language

Isabelle Hupont, Emilia Gomez

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.AI

Comments 8 pages, 5 figures, 2 tables