Foundation Models for Autonomous Driving

Introduction

The 6th edition of the DriveX Workshop focuses on how foundation models and cooperative systems can redefine perception, prediction, planning, and decision-making for autonomous driving and intelligent transportation infrastructure.

Traditional single-vehicle pipelines have achieved impressive progress in 3D detection and tracking, yet they remain constrained by limited viewpoints, occlusions, and domain shifts. Cooperative driving systems, powered by V2X communication and roadside/edge intelligence, extend sensing range, enrich scene context, and enable shared representations across vehicles and infrastructure.

In parallel, foundation models, including vision, vision-language, and multi-modal large models, unlock powerful generalization capabilities: open-vocabulary understanding, scalable pretraining, zero-shot adaptation, and interpretable reasoning about complex road scenes. Emerging end-to-end and agentic systems such as large driving models promise unified perception-to-control frameworks but raise new questions in trustworthiness, reliability, calibration, and evaluation at urban scale.

DriveX 2026 convenes researchers and practitioners from computer vision, robotics, communications, transportation, AI safety, and policy to:

• Design foundation models natively aware of cooperative perception and real-world V2X constraints.
• Bridge large-scale datasets, simulation, and deployment for multi-agent coordination.
• Discuss standards, benchmarks, and open challenges for safe, human-centric cooperative autonomy.

Topics of Interest

• Foundation models and world models for cooperative autonomous driving and intelligent transportation systems
• Vision-Language(-Action) Models for traffic scene understanding and explanation
• LLM- and agent-based support for perception, prediction, planning, and V2X coordination
• Cooperative perception, V2X communication, and infrastructure-assisted driving
• 3D/4D Gaussian Splatting for 3D Scene Reconstruction
• Datasets, benchmarks, and evaluation protocols for foundation models and cooperative perception
• 3D scene understanding and reasoning
• End-to-end pipelines and large driving models for multi-agent decision-making
• Safety, robustness, uncertainty estimation, and open-set reasoning in cooperative systems
• Vehicle-to-Infrastructure (V2I) and Vehicle-to-Everything (V2X) interaction and standards

Schedule (Tentative)

Final schedule, room allocation, and speaker order will be announced closer to the workshop date.

Confirmed Keynote Speakers and Panelists (Academic Track)

Prof. Cordelia Schmid

INRIA, France

Prof. Dr. Daniel Cremers

Technical University of Munich, Germany

Prof. Andreas Geiger

Uni. of Tübingen, Germany

Prof. Davide Scaramuzza

Uni. of Zurich (UZH), Switzerland

Prof. Dr. Manmohan Chandraker

University of California San Diego (UCSD), USA

Prof. Dr. Angela Dai

Technical University of Munich, Germany

Prof. Dr. Jiaqi Ma

University of California Los Angeles (UCLA), USA

Confirmed Keynote Speakers and Panelists (Industry Track)

Prof. Marco Pavone

Stanford Uni. & NVIDIA, USA

Dr. Boris Ivanovic

NVIDIA, USA

Dr. José M. Álvarez

NVIDIA, USA

Prof. Laura Leal-Taixé

NVIDIA, USA

Dr. Balajee Kannan

Motional, USA

Dr. Mingxing Tan

Waymo, USA

PD Dr. habil. Federico Tombari

Google, USA

Ashok Elluswamy

Tesla, USA

Dr. Vittorio Ferrari

Meta, Switzerland

Dr. Erik Rosén

Zenseact, Sweden

Paper Track

DriveX 2026 invites high-quality contributions on foundation models, V2X-based cooperative perception, large driving models, and related topics outlined above.

We welcome:

• Novel full papers (max. 14 pages, excluding references) for publication in the official proceedings.
• 4-6 page extended abstracts or 8-14 page versions (excluding references) of recently published work (non-archival, not included in proceedings).

Submissions must follow the official ECCV 2026 style: LaTeX or Typst.

📘 Archival Track (Proceedings Track)

• Paper Type: Full papers (max. 14 pages, excluding references)
• Included in Proceedings: Yes (archival)
• Submission Opens: April 15, 2026
• Submission Deadline: July 15, 2026 (23:59 PST)
• Notification to Authors: August 1, 2026
• Camera-Ready Deadline: August 15, 2026 (23:59 PST)

📗 Non-Archival Track

• Paper Type: 4-6 page extended abstracts or 8-14 page versions of recently published work (excluding references)
• Included in Proceedings: No (non-archival)
• Submission Opens: April 15, 2026
• Submission Deadline: July 31, 2026 (23:59 PST)
• Notification to Authors: August 15, 2026
• Camera-Ready Deadline: August 31, 2026 (23:59 PST)

Paper Awards

• 🏆 Best Paper Award: $500
• 🏆 Best Paper Runner-Up Award: $300
• 🏆 Best Application Paper Award: $200
• 🏆 Best Poster Award Certificate
• 🏆 Best Keynote Presentation Award Certificate
• 🏆 Best Reviewer Award Certificate

Challenge Awards

• 🏆 TUMTraf-V2X Challenge Winner Award: $500
• 🏆 MDrive Challenge Winner Award: $500
• 🥇 Mixed Signals Challenge 1st Place: $500
• 🥈 Mixed Signals Challenge 2nd Place: $300
• 🥉 Mixed Signals Challenge 3rd Place: $200

• Track 1 - TUMTraf-V2X Challenge: V2I-Based Cooperative Perception
  Infrastructure–vehicle fusion using TUMTraf-V2X. Focus on cooperative 3D detection and tracking with infrastructure-mounted LiDAR, radar, and cameras, emphasizing occlusion handling, long-range awareness, and reliability under real-world conditions.

• Track 2 - doScenes Challenge: Natural Language Instruction for Human Interaction and Vision-Language Navigation
  Built upon doScenes. Participants design models for natural language instructions and visual language navigation to facilitate research on human-vehicle instruction interactions.

• Track 3 - MDrive Challenge: Multi-Agent Reasoning
  Using MDrive teams explore a cooperative driving benchmark for end-to-end closed-loop multi-agent systems.

• Track 4 - nuReasoning Challenge: Reasoning-intensive Long-Tail Driving Scenarios
  The nuReasoning Challenge aims to develop autonomous driving agents that can robustly handle rare interactions and complex causal dependencies, going beyond average-case perception and planning

• Track 5 - HetroD Challenge: Traffic Simulation in Heterogeneous Traffic
  The HetroD Challenge focuses on multi-agent traffic simulation in highly heterogeneous urban environments, based on HetroD dataset.

• Track 6 - UrbanTwin Sim2Real LiDAR Challenge: LUMPI Dataset
  The UrbanTwin I Challenge focuses on reducing the sim-to-real gap in LiDAR data based on the LUMPI dataset.

• Track 7 - UrbanTwin Sim2Real LiDAR Challenge: V2X-Real Dataset
  The UrbanTwin II Challenge focuses on reducing the sim-to-real gap in LiDAR data based on the V2X-Real dataset.

• Track 8 - Mixed Signals: V2X Collaborative 3D Object Detection
  The Mixed Signals Challenge focuses on collaborative 3D object detection using heterogeneous LiDAR data from connected autonomous vehicles and roadside units, emphasizing multi-agent fusion under diverse real-world V2X conditions.

Competition Timeline

• Competition Announcement: May 20, 2026
• Competition Start: August 1, 2026 (4 weeks)
• Submission Deadline: August 29, 2026 (23:59 PST)
• Notification to Participants: September 1, 2026

Top-performing teams will be invited to present at the workshop and will receive money prizes ($2,000 prize pool) and award certificates. Detailed rules, baselines, and submission instructions are available on the official challenge page. Teams should also submit a 4-8 page challenge report, the code, model weights/checkpoints and docker files to be eligible for the prize.

Main Organizers

Dr. Walter Zimmer

University of California, Los Angeles & Technical University of Munich

Dr. Rui Song

University of California, Los Angeles & University of Cambridge

Dr. Zhiyu Huang

University of California, Los Angeles

Dr. Xuewei Qi

Motional Inc.

Dr. Yiluan Guo

Motional Inc.

Zewei Zhou

University of California, Los Angeles

Yu-Hsiang Chen

National Yang Ming Chiao Tung University (NYCU) and University of California, Berkeley (UCB)

Prof. Ross Greer

University of California, Merced

Prof. Yi-Ting Chen

National Yang Ming Chiao Tung University (NYCU)

Prof. Alina Roitberg

University of Hildesheim

Prof. Holger Caesar

Delft University of Technology

Prof. Jiaqi Ma

University of California, Los Angeles

Additional Organizers

Yun Zhang

University of California, Los Angeles

Tianhui Cai

University of California, Los Angeles

Seth Z. Zhao

University of California, Los Angeles

Dr. Xu Han

University of California, Los Angeles

Dr. Zhaoliang Zheng

University of California, Los Angeles

Dr. Hu Cao

Technical University of Munich

Dr. Chuheng Wei

Purdue University

Max Ronecker

NVIDIA

Dr. Stephany Berrio Perez

The University of Sydney

Dr. Xiangyu Chen

NVIDIA

Lena Wild

KTH & Stanford Uni.

Xiangbo Gao

Texas A&M University

Dr. Haibao Yu

The University of Hong Kong

Dr. Larissa Triess

Google

Xingcheng Zhou

Technical University of Munich

Jiajie Zhang

Technical University of Munich

Dr. Mao Shan

The University of Sydney

Dr. Lars Ullrich

Friedrich-Alexander-Universität Erlangen-Nürnberg

Peizheng Li

University of Tübingen & Mercedes-Benz

Prof. Olaf Wysocki

University of Cambridge

Prof. Zhengzhong Tu

Texas A&M University

Prof. Alina Roitberg

University of Hildesheim

Prof. Daniel Watzenig

Graz University of Technology

Prof. Guoyuan Wu

University of California, Riverside

Prof. Holger Caesar

Delft University of Technology

Prof. Bolei Zhou

University of California, Los Angeles and Coco Robotics

Prof. Mohan Trivedi

University of California, San Diego

Prof. Alois C. Knoll

Technical University of Munich

Invited Program Committee

Sponsors

DriveX 2026 welcomes sponsorship from industry, startups, and institutions interested in foundation models, cooperative perception, simulation, and large-scale autonomous driving systems.

For sponsorship opportunities, please contact: wz@ucla.edu.