# NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving

arXiv: https://arxiv.org/abs/2603.06254 · HTML: https://mlsanity.com/paper/2603.06254/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLMs for autonomous driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 31 of its 34 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Placed in

- End-to-end autonomous driving / [VLMs for autonomous driving](https://mlsanity.com/driving/vlms-for-autonomous-driving/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting](https://mlsanity.com/paper/2305.05938/) (2023)
- [EagerMOT: 3D Multi-Object Tracking via Sensor Fusion](https://mlsanity.com/paper/2104.14682/) (2021)
- [AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics](https://mlsanity.com/paper/2008.08063/) (2020)
- [OVTrack: Open-Vocabulary Multiple Object Tracking](https://mlsanity.com/paper/2304.08408/) (2023)
- [CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection](https://mlsanity.com/paper/2310.02960/) (2023)
- [Recurrent Autoregressive Networks for Online Multi-Object Tracking](https://mlsanity.com/paper/1711.02741/) (2017)
- [Towards Long-Tailed 3D Detection](https://mlsanity.com/paper/2211.08691/) (2022)
- [Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments](https://mlsanity.com/paper/2403.13556/) (2024)
- [FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection](https://mlsanity.com/paper/2312.14465/) (2023)
- [MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving](https://mlsanity.com/paper/2409.16149/) (2024)
- [ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images](https://mlsanity.com/paper/2410.24001/) (2024)
- [OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2503.10616/) (2025)
- [Tracking Meets Large Multimodal Models for Driving Scenario Understanding](https://mlsanity.com/paper/2503.14498/) (2025)
- [VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking](https://mlsanity.com/paper/2410.08529/) (2024)
- [Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking](https://mlsanity.com/paper/2410.01678/) (2024)

## Abstract (arXiv)

Generalizing across unknown targets is critical for open-world perception, yet existing 3D Multi-Object Tracking (3D MOT) pipelines remain limited by closed-set assumptions and ``semantic-blind'' heuristics. To address this, we propose Next-step Open-Vocabulary Autoregression (NOVA), an autoregressive association formulation that shifts the data association stage from fragmented distance-based matching toward trajectory-conditioned spatio-semantic modeling. NOVA reformulates 3D trajectories as structured spatio-temporal semantic sequences, enabling the simultaneous encoding of physical motion continuity and deep linguistic priors. By leveraging the autoregressive capabilities of Large Language Models (LLMs), we transform the tracking task into a principled process of next-step sequence completion. This mechanism allows the model to explicitly utilize the hierarchical structure of language space to resolve fine-grained semantic ambiguities and maintain identity consistency across complex long-range sequences through high-level commonsense reasoning. Extensive experiments on nuScenes, V2X-Seq-SPD, and KITTI demonstrate the superior performance of NOVA. Notably, on the nuScenes dataset, NOVA achieves an AMOTA of 22.41% for Novel categories, yielding a significant 20.21% absolute improvement over the baseline. These gains are realized through a compact 0.5B autoregressive model. Code will be available at https://github.com/xifen523/NOVA.