GPT-4V Takes the Wheel: Evaluating Promise and Challenges for Pedestrian Behavior Prediction
Existing pedestrian behavior prediction methods rely primarily on deep neural networks that
utilize features extracted from video frame sequences. Although these vision-based models …
utilize features extracted from video frame sequences. Although these vision-based models …
Graph structure-based implicit risk reasoning for Long-tail scenarios of automated driving
With the development of Artificial Intelligence (AI) technology, autonomous vehicles (AVs)
have entered the general public's view, however, the challenges brought by" long-tail" …
have entered the general public's view, however, the challenges brought by" long-tail" …
The Privacy Pillar--A Conceptual Framework for Foundation Model-based Systems
AI and its relevant technologies, including machine learning, deep learning, chatbots, virtual
assistants, and others, are currently undergoing a profound transformation of development …
assistants, and others, are currently undergoing a profound transformation of development …
Human-like Guidance by Generating Navigation Using Spatial-Temporal Scene Graph
H Suzuki, K Shimomura, T Hirakawa… - 2024 IEEE Intelligent …, 2024 - ieeexplore.ieee.org
Vehicle navigation systems use both GPS and map data, primarily information derived from
map data. Conventional navigation systems assume that the user will look directly at the …
map data. Conventional navigation systems assume that the user will look directly at the …
Precise and Robust Sidewalk Detection: Leveraging Ensemble Learning to Surpass LLM Limitations in Urban Environments
This study aims to compare the effectiveness of a robust ensemble model with the state-of-
the-art ONE-PEACE Large Language Model (LLM) for accurate detection of sidewalks …
the-art ONE-PEACE Large Language Model (LLM) for accurate detection of sidewalks …
Driving Style Alignment for LLM-powered Driver Agent
R Yang, X Zhang, A Fernandez-Laaksonen… - arXiv preprint arXiv …, 2024 - arxiv.org
Recently, LLM-powered driver agents have demonstrated considerable potential in the field
of autonomous driving, showcasing human-like reasoning and decision-making abilities …
of autonomous driving, showcasing human-like reasoning and decision-making abilities …
Words in Motion: Representation Engineering for Motion Forecasting
OS Tas, R Wagner - arXiv preprint arXiv:2406.11624, 2024 - arxiv.org
Motion forecasting transforms sequences of past movements and environment context into
future motion. Recent methods rely on learned representations, resulting in hidden states …
future motion. Recent methods rely on learned representations, resulting in hidden states …
WDMoE: Wireless Distributed Large Language Models with Mixture of Experts
Large Language Models (LLMs) have achieved significant success in various natural
language processing tasks, but how wireless communications can support LLMs has not …
language processing tasks, but how wireless communications can support LLMs has not …
A Superalignment Framework in Autonomous Driving with Large Language Models
Over the last year, significant advancements have been made in the realms of large
language models (LLMs) and multi-modal large language models (MLLMs), particularly in …
language models (LLMs) and multi-modal large language models (MLLMs), particularly in …
Multi-Modal GPT-4 Aided Action Planning and Reasoning for Self-driving Vehicles
Explainable decision-making is critical for building trust in autonomous vehicles. We
investigate the use of a pre-trained large language model (LLM) to derive comprehensible …
investigate the use of a pre-trained large language model (LLM) to derive comprehensible …