# VLM-3D:End-to-End Vision-Language Models for Open-World 3D Perception

arXiv: https://arxiv.org/abs/2508.09061 · HTML: https://mlsanity.com/paper/2508.09061/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Contextual Object Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2305.18279/) (2023)
- [OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models](https://mlsanity.com/paper/2402.10670/) (2024)
- [Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts](https://mlsanity.com/paper/2410.05963/) (2024)
- [Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2211.00849/) (2022)
- [VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2409.20146/) (2024)
- [Measuring Human Perception to Improve Open Set Recognition](https://mlsanity.com/paper/2209.03519/) (2022)

## Built on by (most cited first, 3 of 3)

- [SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery](https://mlsanity.com/paper/2512.07733/) (2025)
- [Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning](https://mlsanity.com/paper/2511.16160/) (2025)
- [OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping](https://mlsanity.com/paper/2607.00881/) (2026)

## Abstract (arXiv)

Open-set perception in complex traffic environments poses a critical challenge for autonomous driving systems, particularly in identifying previously unseen object categories, which is vital for ensuring safety. Visual Language Models (VLMs), with their rich world knowledge and strong semantic reasoning capabilities, offer new possibilities for addressing this task. However, existing approaches typically leverage VLMs to extract visual features and couple them with traditional object detectors, resulting in multi-stage error propagation that hinders perception accuracy. To overcome this limitation, we propose VLM-3D, the first end-to-end framework that enables VLMs to perform 3D geometric perception in autonomous driving scenarios. VLM-3D incorporates Low-Rank Adaptation (LoRA) to efficiently adapt VLMs to driving tasks with minimal computational overhead, and introduces a joint semantic-geometric loss design: token-level semantic loss is applied during early training to ensure stable convergence, while 3D IoU loss is introduced in later stages to refine the accuracy of 3D bounding box predictions. Evaluations on the nuScenes dataset demonstrate that the proposed joint semantic-geometric loss in VLM-3D leads to a 12.8% improvement in perception accuracy, fully validating the effectiveness and advancement of our method.