大模型对齐与安全

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models

Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu

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

All Artificial, Less Intelligence: GenAI through the Lens of Formal Verification

Deepak Narayan Gadde, Aman Kumar, Thomas Nalapat, Evgenii Rezunov, Fabio Cappellini

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments Published in DVCon U.S. 2024

Csi-LLM: A Novel Downlink Channel Prediction Method Aligned with LLM Pre-Training

Shilong Fan, Zhenyu Liu, Xinyu Gu, Haozhen Li

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

Real-Time Automated donning and doffing detection of PPE based on Yolov4-tiny

Anusha Verma, Ghazal Ghajari, K M Tawsik Jawad, Hugh P. Salehi, Fathi Amsaad

专题命中 其他安全 ：safety(abstract)；分类 cs.CY

InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models

Shanglin Lei, Guanting Dong, Xiaoping Wang, Keheng Wang, Runqi Qiao, Sirui Wang

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

An Edge AI System Based on FPGA Platform for Railway Fault Detection

Jiale Li, Yulin Fu, Dongwei Yan, Sean Longyu Ma, Chiu-Wing Sham

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments Accepted at the 2024 IEEE 13th Global Conference on Consumer Electronics (GCCE 2024)

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

Chi-Min Chan, Jianxuan Yu, Weize Chen, Chunyang Jiang, Xinyu Liu, Weijie Shi, Zhiyuan Liu, Wei Xue, Yike Guo

专题命中 其他安全 ：safety(abstract)；分类 cs.CL

Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos

Jiajun Fei, Dian Li, Zhidong Deng, Zekun Wang, Gang Liu, Hui Wang

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

Comments 10 pages, 5 figures

LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models

Qihang Ge, Wei Sun, Yu Zhang, Yunhao Li, Zhongpeng Ji, Fengyu Sun, Shangling Jui, Xiongkuo Min, Guangtao Zhai

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

SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction

Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments Accepted at IV-2024. 13 pages, 5 figures

Enhanced Prediction of Multi-Agent Trajectories via Control Inference and State-Space Dynamics

Yu Zhang, Yongxiang Zou, Haoyu Zhang, Zeyu Liu, Houcheng Li, Long Cheng

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment

Kun Luo, Minghao Qin, Zheng Liu, Shitao Xiao, Jun Zhao, Kang Liu

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

Comments Submitted to EMNLP24

UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages

Trinh Pham, Khoi M. Le, Luu Anh Tuan

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

Comments First two authors contribute equally. Accepted at ACL 2024

2-Level Reinforcement Learning for Ships on Inland Waterways: Path Planning and Following

Martin Waltz, Niklas Paulig, Ostap Okhrin

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

ARMADA: Attribute-Based Multimodal Data Augmentation

Xiaomeng Jin, Jeonghwan Kim, Yu Zhou, Kuan-Hao Huang, Te-Lin Wu, Nanyun Peng, Heng Ji

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

Simulating Field Experiments with Large Language Models

Yaoyu Chen, Yuheng Hu, Yingda Lu

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

Comments 17 pages, 5 figures, 6 tables

PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding

Dawei Dai, Yuanhui Zhang, Long Xu, Qianlan Yang, Xiaojing Shen, Shuyin Xia, Guoyin Wang

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

Comments 8 pages, 4 figs

TR2MTL: LLM based framework for Metric Temporal Logic Formalization of Traffic Rules

Kumar Manas, Stefan Zwicklbauer, Adrian Paschke

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments Accepted for publication in Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Jeju Island - Korea, 2-5 June 2024

FuseChat: Knowledge Fusion of Chat Models

Fanqi Wan, Longguang Zhong, Ziyi Yang, Ruijun Chen, Xiaojun Quan

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

Comments Work in progress

Learning-based Models for Vulnerability Detection: An Extensive Study

Chao Ni, Liyu Shen, Xiaodan Xu, Xin Yin, Shaohua Wang

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 13 pages, 5 figures

An insertable glucose sensor using a compact and cost-effective phosphorescence lifetime imager and machine learning

Artem Goncharov, Zoltan Gorocs, Ridhi Pradhan, Brian Ko, Ajmal Ajmal, Andres Rodriguez, David Baum, Marcell Veszpremi, Xilin Yang, Maxime Pindrys, Tianle Zheng, Oliver Wang, Jessica C. Ramella-Roman, Michael J. McShane, Aydogan Ozcan

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

Comments 24 Pages, 4 Figures

Journal ref ACS Nano (2024)

Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas

Louis Kwok, Michal Bravansky, Lewis D. Griffin

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

Comments 18 pages, 8 figures, Published as a conference paper at COLM 2024

When to Accept Automated Predictions and When to Defer to Human Judgment?

Daniel Sikar, Artur Garcez, Tillman Weyde, Robin Bloomfield, Kaleem Peeroo

专题命中 其他安全 ：safety(abstract)；分类 cs.LG

Comments 9 pages, 10 figures, 3 tables

Animate, or Inanimate, That is the Question for Large Language Models

Leonardo Ranaldi, Giulia Pucci, Fabio Massimo Zanzotto

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

SimCT: A Simple Consistency Test Protocol in LLMs Development Lifecycle

Fufangchen Zhao, Guoqiang Jin, Rui Zhao, Jiangheng Huang, Fei Tan

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

Instruction-tuning Aligns LLMs to the Human Brain

Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimpf, Antoine Bosselut

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

Comments COLM 2024

Exploring the extent of similarities in software failures across industries using LLMs

Martin Detloff

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems

Renzhi Wang, Zhehua Zhou, Jiayang Song, Xuan Xie, Xiaofei Xie, Lei Ma

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Cooperation and Control in Delegation Games

Oliver Sourbut, Lewis Hammond, Harriet Wood

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

Comments Published at IJCAI 2024

A Novel Hybrid Approach for Tornado Prediction in the United States: Kalman-Convolutional BiLSTM with Multi-Head Attention

Jiawei Zhou

专题命中 其他安全 ：safety(abstract)；分类 cs.LG