大模型对齐与安全

CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents

Siyuan Qi, Shuo Chen, Yexin Li, Xiangyu Kong, Junqi Wang, Bangcheng Yang, Pring Wong, Yifan Zhong, Xiaoyuan Zhang, Zhaowei Zhang, Nian Liu, Wei Wang, Yaodong Yang, Song-Chun Zhu

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

Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach

Juanwu Lu, Wei Zhan, Masayoshi Tomizuka, Yeping Hu

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments Accepted at AISTATS 2024

Evaluating Biases in Context-Dependent Health Questions

Sharon Levy, Tahilin Sanchez Karver, William D. Adler, Michelle R. Kaufman, Mark Dredze

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

Online Learning of Human Constraints from Feedback in Shared Autonomy

Shibei Zhu, Tran Nguyen Le, Samuel Kaski, Ville Kyrki

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Accepted to AAAI-24 Bridge Program on Collaborative AI and Modeling of Humans & AAAI-24 Workshop on Ad Hoc Teamwork

In-Memory Learning: A Declarative Learning Framework for Large Language Models

Bo Wang, Tianxiang Sun, Hang Yan, Siyin Wang, Qingyuan Cheng, Xipeng Qiu

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

A Scoping Review of Energy-Efficient Driving Behaviors and Applied State-of-the-Art AI Methods

Zhipeng Ma, Bo Nørregaard Jørgensen, Zheng Ma

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Journal ref Energies 2024, 17, 500

RCoCo: Contrastive Collective Link Prediction across Multiplex Network in Riemannian Space

Li Sun, Mengjie Li, Yong Yang, Xiao Li, Lin Liu, Pengfei Zhang, Haohua Du

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

Comments Accepted by Springer International Journal of Machine Learning and Cybernetics (JMLC), 2024

Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs

Chaoquan Jiang, Jinqiang Wang, Rui Hu, Jitao Sang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments 10 pages,8 figures

Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound

Haoran Dou, Xin Yang, Jikuan Qian, Wufeng Xue, Hao Qin, Xu Wang, Lequan Yu, Shujun Wang, Yi Xiong, Pheng-Ann Heng, Dong Ni

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

Comments 9 pages, 5 figures, 1 table. Accepted by MICCAI 2019 (oral)

Predicting UAV Type: An Exploration of Sampling and Data Augmentation for Time Series Classification

Tarik Crnovrsanin, Calvin Yu, Dane Hankamer, Cody Dunne

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments 12 pages, 3 figures, 4 tables, submitted to IEEE Transactions on Cybernetics

GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks

Mengmei Zhang, Mingwei Sun, Peng Wang, Shen Fan, Yanhu Mo, Xiaoxiao Xu, Hong Liu, Cheng Yang, Chuan Shi

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

A Multi-Fidelity Methodology for Reduced Order Models with High-Dimensional Inputs

Bilal Mufti, Christian Perron, Dimitri N. Mavris

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

Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization

Jiliang Li, Yifan Zhang, Zachary Karas, Collin McMillan, Kevin Leach, Yu Huang

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

Learning High-Quality and General-Purpose Phrase Representations

Lihu Chen, Gaël Varoquaux, Fabian M. Suchanek

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

Comments Findings of EACL 2024

Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models

Safoora Yousefi, Leo Betthauser, Hosein Hasanbeig, Raphaël Millière, Ida Momennejad

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

Reward Bound for Behavioral Guarantee of Model-based Planning Agents

Zhiyu An, Xianzhong Ding, Wan Du

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments To be published in ICLR 24 tiny paper track

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation

Demin Song, Honglin Guo, Yunhua Zhou, Shuhao Xing, Yudong Wang, Zifan Song, Wenwei Zhang, Qipeng Guo, Hang Yan, Xipeng Qiu, Dahua Lin

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

LVCHAT: Facilitating Long Video Comprehension

Yu Wang, Zeyuan Zhang, Julian McAuley, Zexue He

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

Comments 17 pages; 8 figures

Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detection

Genki Osada, Tsubasa Takahashi, Takashi Nishide

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Accepted at AAAI-24

Agents Need Not Know Their Purpose

Paulo Garcia

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

UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models

Ruchao Fan, Natarajan Balaji Shanka, Abeer Alwan

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

Comments Published in IEEE Signal Processing Letters

Pixel Sentence Representation Learning

Chenghao Xiao, Zhuoxu Huang, Danlu Chen, G Thomas Hudson, Yizhi Li, Haoran Duan, Chenghua Lin, Jie Fu, Jungong Han, Noura Al Moubayed

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

How Does Unlabeled Data Provably Help Out-of-Distribution Detection?

Xuefeng Du, Zhen Fang, Ilias Diakonikolas, Yixuan Li

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments ICLR 2024

MADRL-based UAVs Trajectory Design with Anti-Collision Mechanism in Vehicular Networks

Leonardo Spampinato, Enrico Testi, Chiara Buratti, Riccardo Marini

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Accepted for the 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

CNN-FL for Biotechnology Industry Empowered by Internet-of-BioNano Things and Digital Twins

Mohammad, Jamshidi, Dinh Thai Hoang, Diep N. Nguyen

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

SPECTRUM: Speaker-Enhanced Pre-Training for Long Dialogue Summarization

Sangwoo Cho, Kaiqiang Song, Chao Zhao, Xiaoyang Wang, Dong Yu

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

Comments 11 pages, 2 figures

Hyperparameter Optimization for Large Language Model Instruction-Tuning

Christophe Tribes, Sacha Benarroch-Lelong, Peng Lu, Ivan Kobyzev

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

Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems

Yi Dong, Xingyu Zhao, Sen Wang, Xiaowei Huang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Emergent Explainability: Adding a causal chain to neural network inference

Adam Perrett

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

GPT-4V Takes the Wheel: Promises and Challenges for Pedestrian Behavior Prediction

Jia Huang, Peng Jiang, Alvika Gautam, Srikanth Saripalli

专题命中 其他安全 ：safety(abstract)；分类 cs.AI