大模型对齐与安全 - arXivDaily 专题

2503.01261 2025-03-12 cs.CV 78%

Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text

Guotao Liang, Baoquan Zhang, Zhiyuan Wen, Junteng Zhao, Yunming Ye, Kola Ye, Yao He

专题命中其他安全：alignment(title,abstract)

Comments Accepted by CVPR 2025

2503.07593 2025-03-11 cs.CV 78%

Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection

Youjun Zhao, Jiaying Lin, Rynson W. H. Lau

专题命中其他安全：alignment(title,abstract)

Comments AAAI 2025 (Extented Version). Project Page: https://youjunzhao.github.io/HCMA/

2503.06435 2025-03-11 cs.CV 78%

OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection

Adrian Chow, Evelien Riddell, Yimu Wang, Sean Sedwards, Krzysztof Czarnecki

专题命中其他安全：alignment(title,abstract)

2412.12902 2025-03-11 cs.CV 78%

DoPTA: Improving Document Layout Analysis using Patch-Text Alignment

Nikitha SR, Tarun Ram Menta, Mausoom Sarkar

专题命中其他安全：alignment(title,abstract)

2410.00982 2025-03-11 cs.CV 78%

ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding

Liang Shi, Boyu Jiang, Tong Zeng, Feng Guo

专题命中其他安全：safety(title,abstract)

Comments To appear in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

Journal ref Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, 2025, pp. 1061-1071

2503.04478 2025-03-07 cs.CV 78%

Semantic Alignment of Unimodal Medical Text and Vision Representations

Maxime Di Folco, Emily Chan, Marta Hasny, Cosmin I. Bercea, Julia A. Schnabel

专题命中其他安全：alignment(title,abstract)

2406.16783 2025-03-05 cs.CL cs.AI cs.LG 78%

M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models

Rishabh Maheshwary, Vikas Yadav, Hoang Nguyen, Khyati Mahajan, Sathwik Tejaswi Madhusudhan

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

Comments 39 pages

2503.00802 2025-03-04 cs.CV 78%

MFM-DA: Instance-Aware Adaptor and Hierarchical Alignment for Efficient Domain Adaptation in Medical Foundation Models

Jia-Xuan Jiang, Wenhui Lei, Yifeng Wu, Hongtao Wu, Furong Li, Yining Xie, Xiaofan Zhang, Zhong Wang

专题命中其他安全：alignment(title,abstract)

2502.21027 2025-03-03 cs.AR 78%

A RISC-V Multicore and GPU SoC Platform with a Qualifiable Software Stack for Safety Critical Systems

Marc Solé i Bonet, Jannis Wolf, Leonidas Kosmidis

专题命中其他安全：safety(title,abstract)

Comments OSSMPIC2025, 1st workshop on Open Source Solutions for Massively Parallel Integrated Circuits

2409.00862 2025-02-14 cs.HC 78%

User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions

Xianzhe Fan, Qing Xiao, Xuhui Zhou, Jiaxin Pei, Maarten Sap, Zhicong Lu, Hong Shen

专题命中其他安全：alignment(title,abstract)

Comments 19 pages, 1 figure, Accepted by CHI '25

2502.07436 2025-02-12 cs.CV 78%

Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers

Zhaodong Bing, Linze Li, Jiajun Liang

专题命中其他安全：alignment(title,abstract)

2502.05117 2025-02-10 cs.HC 78%

Adoption of AI-Assisted E-Scooters: The Role of Perceived Trust, Safety, and Demographic Drivers

Amit Kumar, Arman Hosseini, Arghavan Azarbayjani, Arsalan Heydarian, Omidreza Shoghli

专题命中其他安全：safety(title,abstract)

2501.15058 2025-01-28 cs.CV 78%

KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained Alignment

Yu Jiang, Yixing Chen, Xingyang Li

专题命中其他安全：alignment(title,abstract)

Comments 7 pages, 5 figures

2501.14683 2025-01-27 cs.SE 78%

An Empirical Study on LLM-based Classification of Requirements-related Provisions in Food-safety Regulations

Shabnam Hassani, Mehrdad Sabetzadeh, Daniel Amyot

专题命中其他安全：safety(title,abstract)

2501.14451 2025-01-27 cs.SE cs.RO 78%

MARL-OT: Multi-Agent Reinforcement Learning Guided Online Fuzzing to Detect Safety Violation in Autonomous Driving Systems

Linfeng Liang, Xi Zheng

专题命中其他安全：safety(title,abstract)

2410.04986 2025-01-22 cs.SE 78%

Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs

Jieke Shi, Zhou Yang, Junda He, Bowen Xu, Dongsun Kim, DongGyun Han, David Lo

专题命中其他安全：safety(title,abstract)

Comments Accepted by ACM Transactions on Software Engineering and Methodology (TOSEM), 35 pages

2501.00877 2025-01-06 cs.CV 78%

FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation

Bingyu Li, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li

专题命中其他安全：alignment(title,abstract)

2501.00917 2025-01-03 cs.CV 78%

Hierarchical Vision-Language Alignment for Text-to-Image Generation via Diffusion Models

Emily Johnson, Noah Wilson

专题命中其他安全：alignment(title,abstract)

2412.16334 2024-12-24 cs.CV 78%

DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment

Cijo Jose, Théo Moutakanni, Dahyun Kang, Federico Baldassarre, Timothée Darcet, Hu Xu, Daniel Li, Marc Szafraniec, Michaël Ramamonjisoa, Maxime Oquab, Oriane Siméoni, Huy V. Vo, Patrick Labatut, Piotr Bojanowski

专题命中其他安全：alignment(title,abstract)

2412.15106 2024-12-20 cs.CV 78%

Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search

Lei Tan, Weihao Li, Pingyang Dai, Jie Chen, Liujuan Cao, Rongrong Ji

专题命中其他安全：alignment(title,abstract)

2408.14512 2024-12-20 cs.LG cs.AI cs.CL 78%

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Duo Wang, Yuan Zuo, Fengzhi Li, Junjie Wu

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

2412.00862 2024-12-03 cs.CV eess.SP 78%

Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication with Visual Feature Alignment

Songjie Xie, Hengtao He, Shenghui Song, Jun Zhang, Khaled B. Letaief

专题命中其他安全：alignment(title,abstract)

2408.17089 2024-12-03 physics.chem-ph quant-ph 78%

Machine learning for predicting control landscape maps of quantum molecular dynamics: Laser-induced three-dimensional alignment of asymmetric top molecules

Tomotaro Namba, Yukiyoshi Ohtsuki

专题命中其他安全：alignment(title,abstract)

Comments 33 pages, 6 figures, 2 tables

2405.10596 2024-11-28 cs.IR 78%

CELA: Cost-Efficient Language Model Alignment for CTR Prediction

Xingmei Wang, Weiwen Liu, Xiaolong Chen, Qi Liu, Xu Huang, Yichao Wang, Xiangyang Li, Yasheng Wang, Zhenhua Dong, Defu Lian, Ruiming Tang

专题命中其他安全：alignment(title,abstract)

Comments 10 pages, 7 figures

2411.16793 2024-11-27 cs.CV q-bio.GN 78%

ST-Align: A Multimodal Foundation Model for Image-Gene Alignment in Spatial Transcriptomics

Yuxiang Lin, Ling Luo, Ying Chen, Xushi Zhang, Zihui Wang, Wenxian Yang, Mengsha Tong, Rongshan Yu

专题命中其他安全：alignment(title,abstract)

2411.15673 2024-11-26 cs.CV 78%

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

Alvi Md Ishmam, Christopher Thomas

专题命中其他安全：alignment(title,abstract)

Comments CVPR 2024

2411.09691 2024-11-15 cs.CV 78%

Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models

Wei Wang, Zhaowei Li, Qi Xu, Linfeng Li, YiQing Cai, Botian Jiang, Hang Song, Xingcan Hu, Pengyu Wang, Li Xiao

专题命中其他安全：alignment(title,abstract)

2410.21511 2024-11-05 econ.GN q-fin.EC 78%

Safety and Security Dynamics in Gulf Cooperation Council (GCC) Countries: A Machine Learning Approach to Forecasting Security Trends

Mahdi Goldani

专题命中其他安全：safety(title,abstract)

2410.20288 2024-10-29 eess.SY cs.SY 78%

Who is Responsible? Explaining Safety Violations in Multi-Agent Cyber-Physical Systems

Luyao Niu, Hongchao Zhang, Dinuka Sahabandu, Bhaskar Ramasubramanian, Andrew Clark, Radha Poovendran

专题命中其他安全：safety(title,abstract)

2408.12706 2024-10-21 physics.med-ph eess.IV 78%

Free-breathing 3D cardiac extracellular volume (ECV) mapping using a linear tangent space alignment (LTSA) model

Wonil Lee, Paul Kyu Han, Thibault Marin, Ismaël B. G. Mounime, Samira Vafay Eslahi, Yanis Djebra, Didi Chi, Felicitas J. Bijari, Marc D. Normandin, Georges El Fakhri, Chao Ma

专题命中其他安全：alignment(title,abstract)

Comments 4496 words, 10 figures, 10 supporting information figures

1. 其他安全 8017 篇

Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text

Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection

OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection

DoPTA: Improving Document Layout Analysis using Patch-Text Alignment

ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding

Semantic Alignment of Unimodal Medical Text and Vision Representations

M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models

MFM-DA: Instance-Aware Adaptor and Hierarchical Alignment for Efficient Domain Adaptation in Medical Foundation Models

A RISC-V Multicore and GPU SoC Platform with a Qualifiable Software Stack for Safety Critical Systems

User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions

Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers

Adoption of AI-Assisted E-Scooters: The Role of Perceived Trust, Safety, and Demographic Drivers

KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained Alignment

An Empirical Study on LLM-based Classification of Requirements-related Provisions in Food-safety Regulations

MARL-OT: Multi-Agent Reinforcement Learning Guided Online Fuzzing to Detect Safety Violation in Autonomous Driving Systems

Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs

FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation

Hierarchical Vision-Language Alignment for Text-to-Image Generation via Diffusion Models

DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment

Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication with Visual Feature Alignment

Machine learning for predicting control landscape maps of quantum molecular dynamics: Laser-induced three-dimensional alignment of asymmetric top molecules

CELA: Cost-Efficient Language Model Alignment for CTR Prediction

ST-Align: A Multimodal Foundation Model for Image-Gene Alignment in Spatial Transcriptomics

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models

Safety and Security Dynamics in Gulf Cooperation Council (GCC) Countries: A Machine Learning Approach to Forecasting Security Trends

Who is Responsible? Explaining Safety Violations in Multi-Agent Cyber-Physical Systems

Free-breathing 3D cardiac extracellular volume (ECV) mapping using a linear tangent space alignment (LTSA) model