大模型对齐与安全 - arXivDaily 专题

2407.00979 2024-07-02 cs.CV 78%

Cross-Modal Attention Alignment Network with Auxiliary Text Description for zero-shot sketch-based image retrieval

Hanwen Su, Ge Song, Kai Huang, Jiyan Wang, Ming Yang

专题命中安全评测：alignment(title,abstract)

2311.17600 2024-06-21 cs.CV 78%

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Xin Liu, Yichen Zhu, Jindong Gu, Yunshi Lan, Chao Yang, Yu Qiao

专题命中安全评测：safety(title,abstract)

2405.19009 2024-06-17 cs.CV 78%

Enhancing Vision-Language Model with Unmasked Token Alignment

Jihao Liu, Jinliang Zheng, Boxiao Liu, Yu Liu, Hongsheng Li

专题命中安全评测：alignment(title,abstract)

Comments Accepted by TMLR; Code and models are available at https://github.com/jihaonew/UTA

2405.12933 2024-06-04 cs.CL cs.AI cs.LG 78%

Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs

Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin

专题命中安全评测：alignment(title)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2024, long paper

2405.14113 2024-05-24 eess.IV cs.CV 78%

Multi-modality Regional Alignment Network for Covid X-Ray Survival Prediction and Report Generation

Zhusi Zhong, Jie Li, John Sollee, Scott Collins, Harrison Bai, Paul Zhang, Terrence Healey, Michael Atalay, Xinbo Gao, Zhicheng Jiao

专题命中安全评测：alignment(title,abstract)

2402.05340 2024-05-10 cs.SE 78%

POLARIS: A framework to guide the development of Trustworthy AI systems

Maria Teresa Baldassarre, Domenico Gigante, Marcos Kalinowski, Azzurra Ragone

专题命中安全评测：trustworthy(title,abstract)

Journal ref Conference on AI Engineering Software Engineering for AI (CAIN 2024), April 14--15, 2024, Lisbon, Portugal

2402.12814 2024-04-23 cs.HC 78%

Exploring the Impact of AI Value Alignment in Collaborative Ideation: Effects on Perception, Ownership, and Output

Alicia Guo, Pat Pataranutaporn, Pattie Maes

专题命中安全评测：alignment(title,abstract)

2404.11249 2024-04-18 cs.CV 78%

A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene

Wenbo Zhang, Yifan Zhang, Jianfeng Lin, Binqiang Huang, Jinlu Zhang, Wenhao Yu

专题命中安全评测：alignment(title,abstract)

2404.09555 2024-04-16 cs.CV 78%

AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation

Žiga Babnik, Fadi Boutros, Naser Damer, Peter Peer, Vitomir Štruc

专题命中安全评测：alignment(title,abstract)

Comments IEEE International Workshop on Biometrics and Forensics (IWBF) 2024, pp. 6

2404.07479 2024-04-12 cs.HC 78%

RASSAR: Room Accessibility and Safety Scanning in Augmented Reality

Xia Su, Han Zhang, Kaiming Cheng, Jaewook Lee, Qiaochu Liu, Wyatt Olson, Jon Froehlich

专题命中安全评测：safety(title,abstract)

Comments To Appear in CHI 2024

2403.06471 2024-03-12 cs.CV 78%

Toward Robust Canine Cardiac Diagnosis: Deep Prototype Alignment Network-Based Few-Shot Segmentation in Veterinary Medicine

Jun-Young Oh, In-Gyu Lee, Tae-Eui Kam, Ji-Hoon Jeong

专题命中安全评测：alignment(title,abstract)

2403.06128 2024-03-12 eess.IV cs.CV 78%

Low-dose CT Denoising with Language-engaged Dual-space Alignment

Zhihao Chen, Tao Chen, Chenhui Wang, Chuang Niu, Ge Wang, Hongming Shan

专题命中安全评测：alignment(title,abstract)

Comments 11 pages, 6 figures

2403.05135 2024-03-11 cs.CV 78%

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Xiwei Hu, Rui Wang, Yixiao Fang, Bin Fu, Pei Cheng, Gang Yu

专题命中安全评测：alignment(title,abstract)

Comments Project Page: https://ella-diffusion.github.io/

2207.12515 2024-02-23 cs.IR 78%

A Survey on Trustworthy Recommender Systems

Yingqiang Ge, Shuchang Liu, Zuohui Fu, Juntao Tan, Zelong Li, Shuyuan Xu, Yunqi Li, Yikun Xian, Yongfeng Zhang

专题命中安全评测：trustworthy(title,abstract)

Comments Accepted by ACM Transactions on Recommender Systems (TORS)

2402.13232 2024-02-21 cs.CV cs.RO 78%

A Touch, Vision, and Language Dataset for Multimodal Alignment

Letian Fu, Gaurav Datta, Huang Huang, William Chung-Ho Panitch, Jaimyn Drake, Joseph Ortiz, Mustafa Mukadam, Mike Lambeta, Roberto Calandra, Ken Goldberg

专题命中安全评测：alignment(title,abstract)

2402.05893 2024-02-09 cs.HC 78%

Personalizing Driver Safety Interfaces via Driver Cognitive Factors Inference

Emily S Sumner, Jonathan DeCastro, Jean Costa, Deepak E Gopinath, Everlyne Kimani, Shabnam Hakimi, Allison Morgan, Andrew Best, Hieu Nguyen, Daniel J Brooks, Bassam ul Haq, Andrew Patrikalakis, Hiroshi Yasuda, Kate Sieck, Avinash Balachandran, Tiffany Chen, Guy Rosman

专题命中安全评测：safety(title,abstract)

Comments 12 pages, 7 figures

2111.14185 2024-01-23 cs.CR 78%

MALIGN: Explainable Static Raw-byte Based Malware Family Classification using Sequence Alignment

Shoumik Saha, Sadia Afroz, Atif Rahman

专题命中安全评测：alignment(title,abstract)

2401.00991 2024-01-03 cs.CR 78%

A Novel Evaluation Framework for Assessing Resilience Against Prompt Injection Attacks in Large Language Models

Daniel Wankit Yip, Aysan Esmradi, Chun Fai Chan

专题命中安全评测：prompt injection(title,abstract)

Comments Accepted to be published in the Proceedings of The 10th IEEE CSDE 2023, the Asia-Pacific Conference on Computer Science and Data Engineering 2023

2312.02310 2023-12-06 cs.CV cs.AI cs.CL cs.LG 78%

VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding

Yizhou Wang, Ruiyi Zhang, Haoliang Wang, Uttaran Bhattacharya, Yun Fu, Gang Wu

专题命中安全评测：alignment(title)；分类 cs.CL、cs.AI、cs.LG

2311.17945 2023-12-01 cs.CV 78%

Contrastive Vision-Language Alignment Makes Efficient Instruction Learner

Lizhao Liu, Xinyu Sun, Tianhang Xiang, Zhuangwei Zhuang, Liuren Yin, Mingkui Tan

专题命中安全评测：alignment(title,abstract)

Comments 17 pages, 10 pages for main paper, 7 pages for supplementary

2206.15367 2023-11-29 stat.AP stat.ME 78%

Targeted learning in observational studies with multi-valued treatments: An evaluation of antipsychotic drug treatment safety

Jason Poulos, Marcela Horvitz-Lennon, Katya Zelevinsky, Tudor Cristea-Platon, Thomas Huijskens, Pooja Tyagi, Jiaju Yan, Jordi Diaz, Sharon-Lise Normand

专题命中安全评测：safety(title,abstract)

2310.07438 2023-10-12 cs.CV cs.RO 78%

DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction

Rezaul Karim, Soheil Mohamad Alizadeh Shabestary, Amir Rasouli

专题命中安全评测：alignment(title,abstract)

Comments 6 tables 4 figures

2306.14115 2023-09-12 cs.LG cs.AI cs.CL stat.ME stat.ML 78%

Towards Trustworthy Explanation: On Causal Rationalization

Wenbo Zhang, Tong Wu, Yunlong Wang, Yong Cai, Hengrui Cai

专题命中安全评测：trustworthy(title)；分类 cs.CL、cs.AI、cs.LG

Comments In Proceedings of the 40th International Conference on Machine Learning (ICML) GitHub Repository: https://github.com/onepounchman/Causal-Retionalization

2309.00920 2023-09-06 cs.MA 78%

Trustworthy Distributed Average Consensus based on Locally Assessed Trust Evaluations

Christoforos N. Hadjicostis, Alejandro D. Dominguez-Garcia

专题命中安全评测：trustworthy(title,abstract)

2309.00249 2023-09-04 cs.RO 78%

Suicidal Pedestrian: Generation of Safety-Critical Scenarios for Autonomous Vehicles

Yuhang Yang, Kalle Kujanpaa, Amin Babadi, Joni Pajarinen, Alexander Ilin

专题命中安全评测：safety(title,abstract)

Comments 6 pages; 5 figures; 2 tables

2202.02215 2023-06-22 cs.RO 78%

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

Wenhao Ding, Chejian Xu, Mansur Arief, Haohong Lin, Bo Li, Ding Zhao

专题命中安全评测：safety(title,abstract)

Comments 18 pages, 5 figures. IEEE Transactions on Intelligent Transportation Systems (T-ITS) 2023

2305.11291 2023-05-22 cs.HC 78%

A systematic review of safety-critical scenarios between automated vehicles and vulnerable road users

Aditya Deshmukh, Zifei Wang, Aaron Gunn, Huizhong Guo, Rini Sherony, Fred Feng, Brian Lin, Shan Bao, Feng Zhou

专题命中安全评测：safety(title,abstract)

2304.04514 2023-04-11 cs.CV 78%

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

Lewei Yao, Jianhua Han, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, Hang Xu

专题命中安全评测：alignment(title,abstract)

Comments Accepted to CVPR2023

2303.04986 2023-03-10 cs.HC 78%

Work with AI and Work for AI: Autonomous Vehicle Safety Drivers' Lived Experiences

Mengdi Chu, Keyu Zong, Xin Shu, Jiangtao Gong, Zicong Lu, Kaimin Guo, Xinyi Dai, Guyue Zhou

专题命中安全评测：safety(title,abstract)

Comments 17 pages, 2 figures

Journal ref CHI 2023

2303.02635 2023-03-07 cs.CV cs.MM 78%

VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning

Kang Chen, Xiangqian Wu

专题命中安全评测：alignment(title,abstract)

1. 安全评测 9324 篇

Cross-Modal Attention Alignment Network with Auxiliary Text Description for zero-shot sketch-based image retrieval

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Enhancing Vision-Language Model with Unmasked Token Alignment

Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs

Multi-modality Regional Alignment Network for Covid X-Ray Survival Prediction and Report Generation

POLARIS: A framework to guide the development of Trustworthy AI systems

Exploring the Impact of AI Value Alignment in Collaborative Ideation: Effects on Perception, Ownership, and Output

A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene

AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation

RASSAR: Room Accessibility and Safety Scanning in Augmented Reality

Toward Robust Canine Cardiac Diagnosis: Deep Prototype Alignment Network-Based Few-Shot Segmentation in Veterinary Medicine

Low-dose CT Denoising with Language-engaged Dual-space Alignment

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

A Survey on Trustworthy Recommender Systems

A Touch, Vision, and Language Dataset for Multimodal Alignment

Personalizing Driver Safety Interfaces via Driver Cognitive Factors Inference

MALIGN: Explainable Static Raw-byte Based Malware Family Classification using Sequence Alignment

A Novel Evaluation Framework for Assessing Resilience Against Prompt Injection Attacks in Large Language Models

VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding

Contrastive Vision-Language Alignment Makes Efficient Instruction Learner

Targeted learning in observational studies with multi-valued treatments: An evaluation of antipsychotic drug treatment safety

DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction

Towards Trustworthy Explanation: On Causal Rationalization

Trustworthy Distributed Average Consensus based on Locally Assessed Trust Evaluations

Suicidal Pedestrian: Generation of Safety-Critical Scenarios for Autonomous Vehicles

A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

A systematic review of safety-critical scenarios between automated vehicles and vulnerable road users

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

Work with AI and Work for AI: Autonomous Vehicle Safety Drivers' Lived Experiences

VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning