DriveMind is proposed, an MLLM-based driving framework that keeps several hypotheses about the scene alive at the same time and updates their weights as new frames arrive and improves fine-grained interactive driving abilities such as merging, emergency braking, and give-way.
Yan Shi, Ke-Hua Chen, Jia-Rui Qi et al.· 0 citations
This work proposes TAU-Agent, an agentic retrieval-augmented framework for traffic anomaly understanding that orchestrates two visual perception tools to retrieve and select query-relevant evidence, including captions, temporal intervals, and object trajectories.
Yuqiang Lin, Yan Shi, Sam Lockyer et al.· 1 citation
This paper proposes CrashDiffuser, a closed-loop VLM-guided diffusion framework that decouples semantic collision reasoning from continuous trajectory synthesis through a hierarchical collision-intent interface derived from the requested target contact region.
Shucheng Zhang, Yuang Zhang, Bingzhang Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.