3 citations · 3 across the 9 of their papers we have counts for
3 papers · 1 filter
CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation
Shucheng Zhang, Yuang Zhang, Bingzhang Wang +3
Generating safety-critical scenarios is essential for evaluating autonomous driving systems. However, existing generators primarily focus on inducing collisions and offer limited c…
TAU-R1: Visual Language Model for Traffic Anomaly Understanding
Yuqiang Lin, Kehua Chen, Sam Lockyer +12
Traffic Anomaly Understanding (TAU) is important for traffic safety in Intelligent Transportation Systems. Recent vision-language models (VLMs) have shown strong capabilities in vi…
Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes
Yifan Jiang, Cong Zhang, Bofei Zhang +4
Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy ove…