DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving.
Wenhai WangJiangwei XieChuanyang HuHaoming ZouJianan FanWenwen TongYang WenSilei WuHanming DengZhiqi LiHao TianLewei LuXizhou ZhuXiaogang WangYu QiaoJifeng DaiPublished in: CoRR (2023)
Keyphrases
- multi modal
- language model
- autonomous driving
- language modeling
- n gram
- grand challenge
- query expansion
- language modelling
- information retrieval
- document retrieval
- retrieval model
- probabilistic model
- speech recognition
- smoothing methods
- multi modality
- stereo vision
- test collection
- statistical language models
- document ranking
- audio visual
- translation model
- video search
- relevance model
- vision algorithms
- multiple modalities
- image annotation
- high dimensional
- statistical language modeling
- uni modal
- language models for information retrieval
- urban traffic
- machine learning
- image registration