Introduction
The 7th edition of the full-day DriveX workshop explores advances in Foundation Models and 3D Perception in Cooperative Autonomous Driving (CAD).
This workshop brings together leading researchers and practitioners to discuss cutting-edge developments in large language models (LLMs),
vision-language models (VLMs), vision-language action models (VLAs), and their applications to autonomous driving systems. Topics include
3D object detection, semantic segmentation, sensor fusion, V2X communication, and cooperative perception.
We explore methods to enhance scene understanding, perception accuracy, dataset curation, and novelty detection. By uniting experts across perception,
V2X, and foundation model domains, this workshop aims to foster innovation in cooperative autonomous driving and intelligent transportation systems.
The workshop addresses critical challenges in multi-modal sensor data fusion, vehicle-infrastructure coordination, and intelligent transportation
systems that leverage both onboard and roadside sensing capabilities.
This year, we expanded our focus with the addition of V2X applications, exploring real-world vehicle-to-infrastructure connectivity that extends
past collaborative perception. The workshop provides a platform for discussing V2X for localization, tolling, road safety, monitoring, and data analytics,
bridging the gap between theoretical advances and practical deployment in intelligent transportation systems. Through keynote presentations, panel discussions,
paper presentations, and challenge tracks, DriveX 2026 creates a comprehensive forum for advancing the state-of-the-art in foundation model-driven
cooperative autonomous driving.
Topics of Interest
3D Environment Perception
- 3D Scene Understanding
- 3D Instance Segmentation
- 3D Occupancy Prediction
- 3D Detection and Tracking
Cooperative Perception
- V2X Communication
- Vehicle-Infrastructure Fusion
- Roadside & ITS Sensors (RSUs)
- Multi-modal Sensor Data Fusion
Foundation Models
- LLM-assisted Perception & Prediction
- Vision-Language Models (VLMs)
- FMs for Dataset Curation & Labeling
- FMs for Accident & Novelty Detection
