# Sim-to-Real Traffic Scene Understanding by Decoupling Semantics from Caption Generation with V-JEPA

arXiv: https://arxiv.org/abs/2609.18562 · HTML: https://mlsanity.com/paper/2609.18562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 16 Sep 2026.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [VL-JEPA: Joint Embedding Predictive Architecture for Vision-language](https://mlsanity.com/paper/2512.10942/) (2025)
- [WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding](https://mlsanity.com/paper/2407.15350/) (2024)
- [The 10th AI City Challenge](https://mlsanity.com/paper/2608.17044/) (2026)

## Abstract (arXiv)

Track 2 of the AI City Challenge 2026 requires both visual question answering (VQA) and traffic event description generation under a challenging synthetic-to real domain shift. Existing vision-language approaches often entangle semantic understanding with language generation, making them susceptible to hallucination and inconsistent reasoning across event phases. In this work, we propose a decoupled semantic understanding framework that first resolves predefined traffic questions into structured semantic facts and subsequently uses these facts to guide caption generation. A frozen V-JEPA encoder extracts predictive scene representations, while a lightweight Llama-based predictor produces answers for VQA queries. To improve reliability, we introduce a training-free structured refinement mechanism that exploits statistical priors, inter-question relationships, and temporal event consistency to correct prediction errors. The refined semantic facts are then provided to Qwen3-VL-8B to generate pedestrian and vehicle descriptions for each traffic event. Experimental results on the official 2026 AI City Challenge Track 2 benchmark show that the proposed method achieves 87.09% VQA accuracy and an overall S2 score of 60.0853, ranking first among all participating teams. These results demonstrate that predictive world representations combined with structured semantic refinement enable more accurate and reliable traffic understanding, leading to higher-quality lan guage generation.