The paper presents a decoupled framework for sim-to-real traffic scene understanding, separating semantic fact extraction from caption generation. It uses a frozen V-JEPA encoder for predictive scene representations and a lightweight Llama-based predictor for VQA, followed by a training-free structured refinement that leverages statistical priors, inter-question relationships, and temporal consistency. The refined facts are then fed to Qwen3-VL-8B to produce pedestrian and vehicle descriptions, achieving top performance on the 2026 AI City Challenge Track 2 benchmark with 87.09% VQA accuracy and an overall S2 score of 60.0853.
By Nguyen Hoai Thuong Bui, Thanh Nguyen Vo, Trinh Tra Giang Nguyen, Ha Duc Bui
arXiv:2607. 08745v1 Announce Type: new Abstract: Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering.
By Siddharth Damodharan, Radhika Gupta, Ali Alshami, Ryan Rabinowitz, Jugal Kalita
arXiv:2511.20022v3 Announce Type: replace-cross
Abstract: Recent advancements in multimodal large language models (MLLMs) have shown strong understanding of driving scenes, drawing interest in their...
By Seungjun Yu, Seonho Lee, Namho Kim, Jaeyo Shin, Junsung Park, Wonjeong Ryu, Raehyuk Jung, Hyunjung Shim
arXiv:2608.28762v1 Announce Type: new
Abstract: Recent advances in visual question answering (VQA) and multimodal large language models (MLLMs) have enabled natural-language reasoning over traffic sc...
By Shaozu Ding, Linan Song, Dajiang Suo
High benchmark accuracy does not guarantee genuine use of visual evidence. We study this problem in traffic accident Video Question Answering (VideoQA), where correct answers should depend on scene-specific visual evidence but may instead be inferred from textual shortcuts.
arXiv:2606. 24759v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still face a fundamental trade-off between temporal reasoning and spatial precision.
By Xiaowei Gao, Pengxiang Li, Yitai Cheng, Ruihan Xu, James Haworth, Stephen Law, Yun Ye
arXiv:2607. 11862v1 Announce Type: cross Abstract: Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding.
By Shijie Wang, Honglu Zhou, Ziyang Wang, Ran Xu, Caiming Xiong, Silvio Savarese, Chen Sun, Juan Carlos Niebles
Egocentric vision offers a first-person view of human perception and decision making, yet its potential for traffic-safety prediction remains underexplored. In this work, we study the decoding of pedestrian crossing intentions from short egocentric video clips.
arXiv:2604.12335v2 Announce Type: replace-cross
Abstract: Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as...
By Tanzila Rahman, Renjie Liao, Leonid Sigal
arXiv:2606. 09142v1 Announce Type: cross Abstract: Egocentric vision offers a first-person view of human perception and decision making, yet its potential for traffic-safety prediction remains underexplored.
By Danya Li, Xiang Su, Yan Feng, Rico Krueger
The paper introduces Latent Action Driving Annotations (LADA), a three‑stage pipeline that converts large amounts of unlabelled observation‑trajectory data into a language‑conditioned driving model. First, a latent action model with a vector‑quantised bottleneck learns a compact codebook of vehicle intents. Then, a small set of language‑annotated examples trains a vision‑language translator to map observations and instructions into this codebook, and finally a VLA is trained on observation‑latent‑action pairs across the full corpus. Using less than 5% of language annotations, LADA attains a Driving Score of 87.98 and a Success Rate of 70.46% on Bench2Drive, matching or surpassing fully supervised baselines.
By Alexey Zakharov, Kemal Oksuz, Puneet K. Dokania
Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still face a fundamental trade-off between temporal reasoning and spatial precision. Models that rely on single-frame or low-resolution inputs often miss small, distant, or partially occluded hazards, while language-centric driving models frequently provide limited grounded evidence for their explanations.