6th DriveX Workshop In conjunction with ECCV 2026

Foundation Models for Autonomous Driving

A premier forum uniting academic, industry, and standards communities to shape the next generation of cooperative, foundation-model-driven autonomous driving and intelligent transportation systems.

Wednesday, September 9, 2026 Malmö, Sweden In conjunction with ECCV 2026
Curated keynote lineup from academia & industry
Focus on real-world driving datasets & benchmarks
Safety, robustness, and trustworthy autonomy

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:

Topics of Interest

Schedule (Tentative)

Time Session
08:00 – 08:20 Opening Remarks – Welcome & Workshop Overview
08:20 – 08:40 Keynote 1 - Dr. Walter Zimmer (UCLA & TUM) Keynote
08:40 – 09:00 Keynote 2 - Prof. Jiaqi Ma (UCLA) Keynote
09:00 – 09:20 Keynote 3 - Prof. Angela Dai (TUM) Keynote
09:20 – 09:40 Keynote 4 - Prof. Cordelia Schmid (INRIA) Keynote
09:40 – 10:00 Keynote 6 - Prof. Davide Scaramuzza (UZH) Keynote
10:00 – 10:30 Coffe Break & Poster Session I (Malmo Massan Exhibit Hall)
10:30 – 10:50 Keynote 5 - Prof. Andreas Geiger (Uni. Tübingen) Keynote
10:50 – 11:10 Keynote 7 - Prof. Manmohan Chandraker (UCSD & NEC Labs) Keynote
11:10 – 11:30 Keynote 8 - Prof. Daniel Cremers (TUM) Keynote
11:30 – 12:00 Panel Discussion I: Academic Track Panel
12:00 – 13:00 Lunch Break & Networking (Malmo Arena - Arena Room)
13:00 – 13:20 Keynote 9 - Vassia Simaiaki (Wayve) Keynote
13:20 – 13:40 Keynotes 10 - Dr. Boris Ivanovic (NVIDIA) Keynote
13:40 – 14:00 Keynotes 11 - Dr. José Álvarez (NVIDIA) Keynote
14:00 – 14:20 Keynotes 12 - Dr. Federico Tombari (Google) Keynote
14:20 – 14:40 Keynotes 13 - Dr. Tony (Xuewei) Qi (Motional) Keynote
14:40 – 15:00 Keynotes 14 - Dr. Katie Luo (Waymo) Keynote
15:00 – 16:00 Coffee Break & Poster Session II
16:00 – 16:20 Keynotes 15 - Prof. Laura Leal-Taixé (NVIDIA) Keynote
16:20 – 17:00 Panel Discussion II: Industry Track Panel
17:00 – 17:10 Oral Presentation 1: Post-Training in End-to-End Autonomous Driving: Taxonomy, Methods, and Challenges Oral
17:10 – 17:20 Oral Presentation 2: How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models Oral
17:20 – 17:30 Oral Presentation 3: A Hierarchical World Model for Driving Oral
17:30 – 17:40 Oral Presentation 4: Introducing The KITScenes Multimodal Dataset Oral
17:40 – 17:50 Oral Presentation 5: Emergent 3D Instance Segmentation from Self-Supervised Point Transformers Oral
17:50 – 18:00 Awards Ceremony – Best Paper (1st, 2nd, 3rd), Best Poster, Best Reviewer, Challenge Winners (1st, 2nd, 3rd)
18:00 – 18:10 Closing Remarks & Group Photo
19:00 – 21:00 Workshop Reception & Networking

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

DriveX Workshop Statistics

6th edition

📄 54 archival and non-archival submissions
👀 271 reviewers recruited
📝 208 reviews submitted
🏆 Acceptance rate: 12.8% oral, 62.9% poster
🎙️ 7 academic keynote speakers, 8 industry keynote speakers
👥 12 core organizers, 28 additional organizers
🤝 3 workshop sponsors

📚 Accepted Papers

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:

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

📘 Archival Track (Proceedings Track)

Submit Now

📗 Non-Archival Track

Submit Now

Accepted Papers

Camera-ready PDFs for the archival and non-archival tracks. See also archival OpenReview and non-archival OpenReview.

Archival Track

Post-Training in End-to-End Autonomous Driving: Taxonomy, Methods, and Challenges

Ruining Yang, Leo Muxing Wang, Yixiao Chen, Tongfei Guo, Yi Xu, Can Cui, Zichong Yang, Yitian Zhang, Ziran Wang, Yun Fu, Lili Su Oral

How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models

Victor Besnier, Anh-Quan Cao, Elias Ramzi, Spyros Gidaris, Tuan-Hung VU, Andrei Bursuc, Eloi Zablocki, Matthieu Cord Oral

DriveFaith: A Cross-Model Study of Reasoning--Action Faithfulness in Autonomous Driving

Sai Bhargav Rongali, Kenji Okuma Video recording

MAGneT-3D: Monocular And Domain-Generalizable Temporal 3D Detection

Mohamed Kotb, Johannes Michael Meier, Christoph Reich, Oussema Dhaouadi, Luis Denninger, Daniel Cremers Video recording

Emergent 3D Instance Segmentation from Self-Supervised Point Transformers

Ted Lentsch, Santiago Montiel-Marín, Holger Caesar, Julian F. P. Kooij Oral

Decoupling Geometry and Semantics for Robust Open-Vocabulary 3D Object Detection

Pedro Rafael Angélico Madureira, José Diogo Xavier Monteiro, Luis Filipe Teixeira Poster

VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Prediction

Abdullah Enes Doruk, Hasan Fehmi Ates Poster

When Doing Nothing Wins: Motion Regime Imbalance in In-Cabin Driver Prediction

Likith Prabhu Poster

Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model

Harisankar Babu, Benjamin Coors, Christopher Lang, Hendrik Berkemeyer, Tamim Asfour, Simon Föll Poster

Interpretable Uncertainty-Aware Object Detection with Subjective Logic

Stefan Orf, Valentin Marotta, Svetlana Pavlitska, J. Marius Zöllner Poster

RSG-VLM: An Auditable Radar Scene-Graph Interface for Grounding Vision–Language Models in Driving-Scene Geometry

Bowei Zhang, Shangze Kong Poster

GaussianOcc3D: Adaptive Multi-modal Fusion for 3D Occupancy Prediction Using Gaussians

Abdullah Enes Doruk, Hasan Fehmi Ates Poster

BikeScenes: LiDAR Semantic Segmentation for Bicycles

Denniz Goren, Holger Caesar Poster

SafeLand: Safe Autonomous Landing in Unknown Environments with Bayesian Semantic Mapping

Markus Gross, Andreas Greiner, Sai Bharadhwaj Matha, Felix Soest, Daniel Cremers, Henri Meeß Poster

BRIDGE: Bridging the Modality Gap in Semantic Adversarial Attacks on Vision-Language Models

Roman Prykhodchenko, Joanna Jaworek-Korjakowska Poster

4D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generation

Jimmie Kwok, Holger Caesar, Andras Palffy Poster

PseudoMapLabeler: Confidence-Aware Pseudo-Label Generation for Semi-Supervised Online Mapping

Chikao Tsuchiya, Dhaval Bhanderi, David Ilstrup, Hsin-Min Cheng, Chris J Ostafew Poster

Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City

Adrian Cespedes, Marcelo Chincha, Dunant Cusipuma, Victor Flores-Benites, David Ortega, Arturo Deza Poster

Cooperative Interior-Exterior Perception for Driver Gaze Estimation

Georgios Markos Chatziloizos, Andrea Ancora, Barat Christian, Andrew I. Comport Poster

CMD: Class Margin Dispersion for Post-hoc Misclassification Detection

Anthony Fernando Judeson, Torsten Schön Poster

Inference-Time Attention Steering for Vision-Language-Action Driving Models

Darshan Nagendra Prasad, Lars Ullrich, Knut Graichen Poster

UniDepth-LSS: Depth Foundation Model Priors for Camera-Only BEV Perception

Muhammad Adeel Hafeez, Muhammad Asad, Ganesh Sistu, Michael G. Madden, Ihsan Ullah Poster

NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving

Ashkan Yousefi Zadeh, Zishuo Zhu, Xiaomeng Li, Andry Rakotonirainy, Sebastien Glaser, Ronald Schroeter, Patricia Delhomme, Zahra Mehraban Poster

CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios

Sparsh Garg, Yi-Wen Chen, Vijay Kumar b g, Abhishek Aich Poster

SENSE: Stereo OpEN Vocabulary SEmantic Segmentation

Thomas Campagnolo, Ezio Malis, Philippe Martinet, Gaetan Bahl Poster

CounterDrive: Data-Centric Adaptation of Open VLMs for Counterfactual Driving Reasoning

Yi-Wen Chen, Vijay Kumar b g, Sparsh Garg, Manmohan Chandraker Poster

RedLight-VLA: Models for traffic-rule grounding and behavioral emphasis in driving policies

Bala Murali Manoghar Sai Sudhakar, Sourab Bapu Sridhar, Sandipan Das, Rahul Ahuja, Meda Lazar, Ashish Garg, Pratik Likhar, Senthil Yogamani Poster

Non-Archival Track

A Hierarchical World Model for Driving

Sudhanshu Mittal, Arian Mousakhan, Silvio Galesso, Karim Farid, Johannes Dienert, Rajat Sahay, Thomas Brox Oral

Introducing The KITScenes Multimodal Dataset

Richard Schwarzkopf, Fabian Immel, Alexander Blumberg, Jonas Merkert, Nils Alexander Rack, Kaiwen Wang, Fabian Konstantinidis, Julian Truetsch, Carlos Fernandez, Annika Bätz, Kevin Rösch, Marlon Steiner, Willi Poh, Yinzhe Shen, Royden Wagner, Felix Hauser, Dominik Strutz, Jaime Villa, Gleb Stepanov, Holger Caesar, Ömer Şahin Taş, Frank Bieder, Jan-Hendrik Pauls, Christoph Stiller Oral

SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model

Zewei Zhou, Ruining Yang, Xuewei Qi, Yiluan Guo, Sherry X. Chen, Tao Feng, Kateryna Pistunova, Yishan Shen, Lili Su, Jiaqi Ma Poster

Prospective Geometric Anchoring for Stable and Controllable Long-Horizon Driving World Models

Marius Kästingschäfer, Sudhanshu Mittal, Sebastian Bernhard, Thomas Brox Poster

Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving

Yuan Gao, Mattia Piccinini, Finn Rasmus Schäfer, Qunying Song, Johannes Betz Poster

CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models

Hsu-kuang Chiu, Stephen F Smith Poster

On the Feasibility of Activation Steering for End-to-End Driving

Shu-Wei Lu, Jinsu Yoo, Yu-Hsiang Chen, Yi-Hsuan Tsai, Wei-Lun Chao, Yi-Ting Chen Poster

Meta-Kernel Latent Diffusion for Range-Guided Camera-to-LiDAR Synthesis

Carolin Wunderlich Poster

RadarGen: Automotive Radar Point Cloud Generation from Cameras

Tomer Borreda, Fangqiang Ding, Sanja Fidler, Shengyu Huang, Or Litany Poster

SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation

Hiba Dahmani, Nathan Piasco, Moussab Bennehar, Luis Guillermo Roldao Jimenez, Dzmitry Tsishkou, Laurent Caraffa, Jean-Philippe Tarel, Roland Brémond Poster

HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training

Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson Poster

When the City Teaches the Car: Label-Free 3D Perception from Infrastructure

Zhen Xu, Jinsu Yoo, Cristian Bautista, Zanming Huang, Tai-Yu Pan, Zhenzhen Liu, Katie Z Luo, Mark Campbell, Bharath Hariharan, Wei-Lun Chao Poster

QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception

Seth Z. Zhao, Huizhi Zhang, Zhaowei Li, Juntong Peng, Anthony Chui, Zewei Zhou, Zonglin Meng, Hao Xiang, Zhiyu Huang, Fujia Wang, Ran Tian, Chenfeng Xu, Bolei Zhou, Jiaqi Ma Poster

PDFs open on OpenReview.

Paper Awards

Challenge Awards

Second and third place of each the TUMTraf-V2X and MDrive challenges will receive an award certificate.

DriveX Grand Challenge

Competition Timeline

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

Additional Organizers

Invited Program Committee

Wesley Maia

UC Merced

Bo Yang

UCLA

Dr. Camila Correa-Jullian

UCLA

Prof. Jiachen Li

UC Riverside

Afnan Alofi

Nourah Bint Abdulrahman University

Peizheng Li

Uni Tübingen

Marc Unzueta

Cruise

Kianna Ng

UC Merced

Dr. Wei Cao

Uni. of Illinois at Urbana-Champaign

Angel Martinez-Sanchez

UC Merced

Prof. Ziran Wang

Purdue Uni.

Qiyuan Wu

Cornell Uni

Erika Maquiling

UC Merced

Parthib Roy

UC Merced

Zhenzhen Liu

Cornell Uni.

Kunlin Cai

UCLA

Markus Gross

Fraunhofer IVI & TUM

Prof. Hang Qiu

UC Riverside

Dr. Katie Z Luo

Stanford

Dr.Cheng Perng Phoo

Waymo

Zhenghao Peng

UCLA

Dr. Shiyu Jin

Waymo

Johnson Liu

UCLA

Haoxuan Ma

UCLA

Yifan Liu

UCLA

Jinsu Yoo

OSU

Sponsors

Motional Logo
IEEE Intelligent Transportation Systems Society (ITSS) Logo
University of Central Florida Logo

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.