LLVM-AD @ WACV 2024

The 1st WACV Workshop on Large Language and Vision Models for Autonomous Driving ( LLVM-AD) seeks to bring together academia and industry professionals in a collaborative exploration of applying large language and vision models to autonomous driving. Through a half-day in-person event, the workshop will showcase regular and demo paper presentations and invited talks from famous researchers in academia and industry. Additionally, LLVM-AD will launch two open-source real-world traffic language understanding datasets, catalyzing practical advancements. The workshop will host two challenges based on this dataset to assess the capabilities of language and computer vision models in addressing autonomous driving challenges.

Note for Benchmark: The workshop challenge will be maintained in the long term, and even after the workshop concludes, we will continue to welcome submissions of new results on the datasets. We will also update the benchmark accordingly.

Workshop Recording

Important Dates

• Paper Submission Deadline: October 23rd, 2023 October 26th, 2023
• Author Notification: November 13th, 2023
• Camera-ready Papers Deadline: November 19th, 2023

Invited Speakers

Dr. Zhen Li Assistant Professor, CUHKSZ	Dr. Oleg Sinavski Principal Applied Scientist, Wayve	Dr. Yu Huang CEO and Chief Scientist, roboraction.ai

Organizers

Chao Zheng Tencent	Kun Tang Tencent	Zhipeng Cao Tencent	Xu Cao UIUC	Yunsheng Ma Purdue
Can Cui Purdue	Wenqian Ye UVA	Ziran Wang Purdue	Shawn Mei Tencent	Tong Zhou Tencent

Accepted Papers

Summary of the 1st WACV Workshop on Large Language and Vision Models for Autonomous Driving (LLVM-AD): [Arxiv, GitHub]

🎉 We would like to congrate the following papers for being accepted to LLVM-AD 2024!

• Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles

• Drive Like a Human: Rethinking Autonomous Driving with Large Language Models

• A Game of Bundle Adjustment - Learning Efficient Convergence Accepted as a tech report for ICCV 2023 Paper

• VLAAD: Vision and Language Assistant for Autonomous Driving

• A Safer Vision-based Autonomous Planning System for Quadrotor UAVs with Dynamic Obstacle Trajectory Prediction and Its Application with LLMs

• Human-Centric Autonomous Systems With LLMs for User Command Reasoning

• NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations

• Latency Driven Spatially Sparse Optimization for Multi-Branch CNNs for Semantic Segmentation

• LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localization

Challenge Organization Committee

• Chao Zheng (Tencent)
• Kun Tang (Tencent)
• Zhipeng Cao (Tencent)
• Tong Zhou (Tencent)
• Erlong Li (Tencent)
• Ao Liu (Tencent)
• Shengtao Zou (Tencent)
• Xinrui Yan (Tencent)
• Shawn Mei (Tencent)
• Yunsheng Ma (Purdue University)
• Can Cui (Purdue University)
• Ziran Wang (Purdue University)
• Yang Zhou (New York University)
• Kaizhao Liang (SambaNova Systems)
• Wenqian Ye (PediaMed AI & University of Virginia)
• Xu Cao (PediaMed AI & University of Illinois Urbana-Champaign)

Program Committee

• Erlong Li (Tencent)
• Ao Liu (Tencent)
• Shengtao Zou (Tencent)
• Xinrui Yan (Tencent)
• Yang Zhou (New York University)
• Kaizhao Liang (SambaNova Systems)
• Tianren Gao (SambaNova Systems)
• Kuei-Da Liao (SambaNova Systems)
• Shan Bao (University of Michigan)
• Xuhui Kang (University of Virginia)
• Sean Sung-Wook Lee (University of Virginia)
• Amr Abdelraouf (Toyota Motor North America)
• Jianguo Cao (PediaMed AI)
• Jintai Chen (University of Illinois Urbana-Champaign)

Citation

If the workshop and the survey inspire you, please consider citing our work:

@misc{cui2023survey,
      title={A Survey on Multimodal Large Language Models for Autonomous Driving}, 
      author={Can Cui and Yunsheng Ma and Xu Cao and Wenqian Ye and Yang Zhou and Kaizhao Liang and Jintai Chen and Juanwu Lu and Zichong Yang and Kuei-Da Liao and Tianren Gao and Erlong Li and Kun Tang and Zhipeng Cao and Tong Zhou and Ao Liu and Xinrui Yan and Shuqi Mei and Jianguo Cao and Ziran Wang and Chao Zheng},
      year={2023},
      eprint={2311.12320},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}