# STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision

arXiv: https://arxiv.org/abs/2608.01535 · HTML: https://mlsanity.com/paper/2608.01535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)
- End-to-end autonomous driving / [VLMs for autonomous driving](https://mlsanity.com/driving/vlms-for-autonomous-driving/)

## Builds on (most cited first, 19 of 19)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving](https://mlsanity.com/paper/2312.09245/) (2023)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://mlsanity.com/paper/2503.15558/) (2025)
- [R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes](https://mlsanity.com/paper/2108.04814/) (2021)
- [Segment Any Motion in Videos](https://mlsanity.com/paper/2503.22268/) (2025)
- [Any4D: Unified Feed-Forward Metric 4D Reconstruction](https://mlsanity.com/paper/2512.10935/) (2025)
- [DepthLM: Metric Depth From Vision Language Models](https://mlsanity.com/paper/2509.25413/) (2025)
- [SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models](https://mlsanity.com/paper/2411.13112/) (2024)
- [STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving](https://mlsanity.com/paper/2506.06218/) (2025)
- [Motion Segmentation from a Moving Monocular Camera](https://mlsanity.com/paper/2309.13772/) (2023)
- [On Moving Object Segmentation from Monocular Video with Transformers](https://mlsanity.com/paper/2411.19141/) (2024)
- [Camera-based vehicle velocity estimation from monocular video](https://mlsanity.com/paper/1802.07094/) (2018)
- [DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance](https://mlsanity.com/paper/2508.18506/) (2025)
- [RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Clouds](https://mlsanity.com/paper/2512.10376/) (2025)
- [From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models](https://mlsanity.com/paper/2512.05277/) (2025)

## Abstract (arXiv)

Vision-language models (VLMs) are emerging as a key component of embodied intelligence, with growing applications in auto-labeling and end-to-end autonomous driving. However, existing approaches for improving spatiotemporal reasoning in VLMs often rely on complex preprocessing pipelines, expensive human annotations, or synthetic data, which limit scalability and introduce potential sim-to-real gaps. Moreover, although these methods have improved spatiotemporal understanding, they still lack strong metric reasoning capabilities for dynamic scenes, such as estimating object motion in real-world units. Prior work has explored LiDAR-based metric depth supervision to enhance spatial perception, but it does not directly address temporal reasoning. We introduce STAR-VLM, an automotive radar-supervised framework that enhances spatiotemporal VLMs with motion reasoning and metric velocity estimation for autonomous driving. Automotive radar is a low-cost and widely deployed sensor that provides complementary spatiotemporal supervision through range and Doppler measurements. By leveraging these measurements as label-free ground truth during training, STAR-VLM improves the metric spatiotemporal reasoning ability of VLMs. Through experiments on driving scenarios, we show that STAR-VLM achieves state-of-the-art performance on both motion classification and metric velocity estimation, outperforming even task-specific methods designed for each task. These results highlight automotive radar as a scalable and cost-effective source of supervision for building metric-aware spatiotemporal VLMs for real-world autonomous driving.