Towards Single-System Illusion in Software-Defined Vehicles--Automated, AI-Powered Workflow

K Lebioda, V Vorobev, N Petrovic, F Pan… - arXiv preprint arXiv …, 2024 - arxiv.org
We propose a novel model-and feature-based approach to development of vehicle software
systems, where the end architecture is not explicitly defined. Instead, it emerges from an …

Soft Self-Consistency Improves Language Model Agents

H Wang, A Prasad, E Stengel-Eskin… - arXiv preprint arXiv …, 2024 - arxiv.org
Generations from large language models (LLMs) can be improved by sampling and scoring
multiple solutions to select a final answer. Current" sample and select" methods such as self …

Traffic Performance GPT (TP-GPT): Real-Time Data Informed Intelligent ChatBot for Transportation Surveillance and Management

B Wang, MM Karim, C Liu, Y Wang - arXiv preprint arXiv:2405.03076, 2024 - arxiv.org
The digitization of traffic sensing infrastructure has significantly accumulated an extensive
traffic data warehouse, which presents unprecedented challenges for transportation …