A decision-making model for self-driving vehicles based on GPT-4V, federated reinforcement learning, and blockchain

T Alam, R Gupta, NN Ahamed, A Ullah - Neural Computing and …, 2024 - Springer
Decision-making is crucial in fully autonomous vehicle operations and is expected to greatly
influence future transportation systems. Observing the current driving status of autonomous …

Enhancing traffic prediction with textual data using large language models

X Huang - arxiv preprint arxiv:2405.06719, 2024 - arxiv.org
Traffic prediction is pivotal for rational transportation supply scheduling and allocation.
Existing researches into short-term traffic prediction, however, face challenges in adequately …

Advancing its applications with llms: A survey on traffic management, transportation safety, and autonomous driving

D Zhang, H Zheng, W Yue, X Wang - International Joint Conference on …, 2024 - Springer
In the past two years, large language models (LLMs) have shown extensive attention in the
applications of intelligent transportation systems (ITS). Despite the huge potential, there is …

Subjective Scoring Framework for VQA Models in Autonomous Driving

K Rekanar, A Ahmed, R Mohandas, G Sistu… - IEEE …, 2024 - ieeexplore.ieee.org
The development of vision and language transformer models has paved the way for Visual
Question Answering (VQA) models and related research. There are metrics to assess the …

[HTML][HTML] DDC-Chat: Achieving accurate distracted driver classification through instruction tuning of visual language model

C Liao, K Lin - Journal of Safety Science and Resilience, 2024 - Elsevier
Driver behavior is a critical factor in road safety, highlighting the need for advanced methods
in Distracted Driving Classification (DDC). In this study, we introduce DDC-Chat, a novel …

When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis

R Zhang, B Wang, J Zhang, Z Bian, C Feng… - arxiv preprint arxiv …, 2025 - arxiv.org
The increasing availability of traffic videos functioning on a 24/7/365 time scale has the great
potential of increasing the spatio-temporal coverage of traffic accidents, which will help …

Multimodal AI model for zero-shot vehicle brand identification

C Kerdvibulvech - Multimedia Tools and Applications, 2025 - Springer
Identifying vehicle brands is a crucial aspect of advancing media technology in intelligent
transportation systems, yet it remains challenging due to the wide variety of car models and …

Evaluating the Agreement between Human Preferences, GPT-4V and Gemini Pro Vision Assessments: Can AI Recognise Which Restaurants People Might Like?

D Krupić, D Matijević, N Šuvak, D Ševerdija, J Maltar - 2024 - researchsquare.com
The study aims to introduce a methodology for assessing agreement between AI and human
ratings, specifically focusing on visual large language models (LLMs). It presents empirical …