{"slug": "statebridge-phase-and-track-grounded-reasoning-for-synthetic-to-real-traffic-and", "title": "StateBridge: Phase- and Track-Grounded Reasoning for Synthetic-to-Real Traffic Video Captioning and VQA", "summary": "A research team's StateBridge framework scored an official S2 score of 55.4679 on AI City Challenge 2026 Track 2 while training only on synthetic data, according to the arXiv paper 2610.31898v1. StateBridge combines phase-aware clip construction, pedestrian and vehicle track summaries, and structured prompts to fine-tune public vision-language models on synthetic captioning and visual question answering, then merges outputs through fact-locked caption fusion and evidence-diverse VQA consensus. The result indicates structured evidence transfer can help traffic safety captioning and VQA models generalize from simulated scenes to real-world traffic.", "body_md": "arXiv:2610.31898v1 Announce Type: new \nAbstract: Traffic safety videos provide rich evidence for understanding interactions between pedestrians and vehicles, but synthetic-to-real evaluation makes this setting challenging because models must learn from simulated scenes and generalize to real-world traffic. In this work, we present StateBridge, a traffic video-language framework designed to operate under this synthetic-only training protocol. Our approach uses phase-aware clip construction, pedestrian and vehicle track summaries, and structured prompts to ground vision-language models in stable traffic evidence rather than appearance alone. We fine-tune public vision-language models on synthetic captioning and visual question answering examples, then combine their outputs through fact-locked caption fusion and evidence-diverse VQA consensus to improve consistency across actor roles, behavioral phases, and question types. StateBridge achieves an official S2 score of 55.4679 on AI City Challenge 2026 Track 2 using only synthetic training data. These results demonstrate the effectiveness of structured evidence transfer for traffic safety captioning and visual question answering.", "url": "https://wpnews.pro/news/statebridge-phase-and-track-grounded-reasoning-for-synthetic-to-real-traffic-and", "canonical_source": "https://arxiv.org/abs/2610.31898", "published_at": "2026-10-26 04:00:00+00:00", "updated_at": "2026-10-26 04:12:12.407587+00:00", "lang": "en", "topics": ["computer-vision", "natural-language-processing", "machine-learning", "ai-research"], "entities": ["StateBridge", "AI City Challenge 2026", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/statebridge-phase-and-track-grounded-reasoning-for-synthetic-to-real-traffic-and", "markdown": "https://wpnews.pro/news/statebridge-phase-and-track-grounded-reasoning-for-synthetic-to-real-traffic-and.md", "text": "https://wpnews.pro/news/statebridge-phase-and-track-grounded-reasoning-for-synthetic-to-real-traffic-and.txt", "jsonld": "https://wpnews.pro/news/statebridge-phase-and-track-grounded-reasoning-for-synthetic-to-real-traffic-and.jsonld"}}