大模型对齐与安全

Improving Open Language Models by Learning from Organic Interactions

Jing Xu, Da Ju, Joshua Lane, Mojtaba Komeili, Eric Michael Smith, Megan Ung, Morteza Behrooz, William Ngan, Rashel Moritz, Sainbayar Sukhbaatar, Y-Lan Boureau, Jason Weston, Kurt Shuster

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.AI

CapText: Large Language Model-based Caption Generation From Image Context and Description

Shinjini Ghosh, Sagnik Anupam

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

Comments Update 6/6/23: Fixed typographic error in abstract

Do GPTs Produce Less Literal Translations?

Vikas Raunak, Arul Menezes, Matt Post, Hany Hassan Awadalla

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

Comments ACL 2023

Recent Advances in Graph-based Machine Learning for Applications in Smart Urban Transportation Systems

Hongde Wu, Sen Yan, Mingming Liu

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Reverse Engineering Self-Supervised Learning

Ido Ben-Shaul, Ravid Shwartz-Ziv, Tomer Galanti, Shai Dekel, Yann LeCun

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

Any-to-Any Generation via Composable Diffusion

Zineng Tang, Ziyi Yang, Chenguang Zhu, Michael Zeng, Mohit Bansal

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

Comments Project Page: https://codi-gen.github.io

Accessible Instruction-Following Agent

Kairui Zhou

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

The System Model and the User Model: Exploring AI Dashboard Design

Fernanda Viégas, Martin Wattenberg

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 10 pages, 2 figures

Virus2Vec: Viral Sequence Classification Using Machine Learning

Sarwan Ali, Babatunde Bello, Prakash Chourasia, Ria Thazhe Punathil, Pin-Yu Chen, Imdad Ullah Khan, Murray Patterson

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

Comments 11 Pages 6 Figures Accepted in conference Conference on Health, Inference, and Learning (CHIL) 2023

Machine learning framework for end-to-end implementation of Incident duration prediction

Smrithi Ajit, Varsha R Mouli, Skylar Knickerbocker, Jonathan S. Wood

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

D2CSE: Difference-aware Deep continuous prompts for Contrastive Sentence Embeddings

Hyunjae Lee

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

Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning

Hector Kohler, Riad Akrour, Philippe Preux

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding

Yidan Sun, Qin Chao, Yangfeng Ji, Boyang Li

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

Comments 25 pages, 17 figures

Masked Vision and Language Modeling for Multi-modal Representation Learning

Gukyeong Kwon, Zhaowei Cai, Avinash Ravichandran, Erhan Bas, Rahul Bhotika, Stefano Soatto

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

Comments International Conference on Learning Representations (ICLR) 2023

Teacher-Student Knowledge Distillation for Radar Perception on Embedded Accelerators

Steven Shaw, Kanishka Tyagi, Shan Zhang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments submitted at ASILOMAR,2023

NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks

Wenkai Tan, Justus Renkhoff, Alvaro Velasquez, Ziyu Wang, Lusi Li, Jian Wang, Shuteng Niu, Fan Yang, Yongxin Liu, Houbing Song

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Submitted to IEEE Fuzzy 2023. arXiv admin note: text overlap with arXiv:2303.06032

Generative Modeling Helps Weak Supervision (and Vice Versa)

Benedikt Boecking, Nicholas Roberts, Willie Neiswanger, Stefano Ermon, Frederic Sala, Artur Dubrawski

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

Comments Published as a conference paper at ICLR 2023

Cybersecurity of AI medical devices: risks, legislation, and challenges

Elisabetta Biasin, Erik Kamenjasevic, Kaspar Rosager Ludvigsen

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.CY

HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention

Shijie Geng, Jianbo Yuan, Yu Tian, Yuxiao Chen, Yongfeng Zhang

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

Comments Accepted at ICLR 2023

Do Orcas Have Semantic Language? Machine Learning to Predict Orca Behaviors Using Partially Labeled Vocalization Data

Sophia Sandholm

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.LG

Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues

Mehrad Moradshahi, Victoria Tsai, Giovanni Campagna, Monica S. Lam

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

Comments Published in EACL 2023

CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles using Deep Reinforcement Learning

Jiaying Guo, Long Cheng, Shen Wang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech

Li-Wei Chen, Shinji Watanabe, Alexander Rudnicky

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

Comments Accepted to AAAI 2023

Toward Explainable AI for Regression Models

Simon Letzgus, Patrick Wagner, Jonas Lederer, Wojciech Samek, Klaus-Robert Müller, Gregoire Montavon

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 17 pages, 10 figures, published; changes: 1. references to code and xai-regression.org added (p. 1/2, end of introduction), 2. adjustment of sign-error in restructuring section (p. 8, just above Fig. 4)

Journal ref IEEE Signal Processing Magazine (Volume: 39, Issue: 4, July 2022) 40-58

A Semi-supervised Approach for Activity Recognition from Indoor Trajectory Data

Mashud Rana, Ashfaqur Rahman, Daniel Smith

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Optimized Symbolic Interval Propagation for Neural Network Verification

Philipp Kern, Marko Kleine Büning, Carsten Sinz

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Published at the 1st Workshop on Formal Verification of Machine Learning (WFVML 2022) (https://www.ml-verification.com/)

A machine learning model to identify corruption in México's public procurement contracts

Andrés Aldana, Andrea Falcón-Cortés, Hernán Larralde

专题命中 其他安全 ：safety(abstract)；分类 cs.CY、cs.LG

Comments 17 pages, 8 figures. On revision in Government Information Quarterly

AI Model Utilization Measurements For Finding Class Encoding Patterns

Peter Bajcsy, Antonio Cardone, Chenyi Ling, Philippe Dessauw, Michael Majurski, Tim Blattner, Derek Juba, Walid Keyrouz

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 45 pages, 29 figures, 7 tables

Image-based Artificial Intelligence empowered surrogate model and shape morpher for real-time blank shape optimisation in the hot stamping process

Haosu Zhou, Nan Li

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 32 pages, 11 figures

Land Use Prediction using Electro-Optical to SAR Few-Shot Transfer Learning

Marcel Hussing, Karen Li, Eric Eaton

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

Comments Published at Tackling Climate Change with Machine Learning workshop at NeurIPS 2022