English(EN) From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning

AI研究解决自动驾驶汽车和视频分析中的时间接地问题

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-19 13:18

两篇新研究论文探讨了改进AI系统时间接地的方法，特别是在自动驾驶汽车和视频分析领域。第一篇论文《从提示到路面，穿越时间》（From Prompts to Pavement Through Time）研究了自动驾驶汽车中Agent通信的时间条件，发现虽然它改变了推理，但并未显著提高标准指标，却在危险预测方面显示出定性优势。第二篇论文《Foresee-to-Ground》提出了一个用于视频时间接地的框架，将事件识别与边界测量分开，从而在不同的视频-LLM骨干网络中实现更稳定和可验证的预测。 AI

影响这些论文引入了改进AI在复杂场景中对时间理解的新方法，有望提高自动驾驶系统的安全性以及视频分析的准确性。

排序理由两篇发表在arXiv上的学术论文，详细介绍了AI系统时间接地的新方法。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Ahmed Hussein · 2026-05-19 13:18

From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning

Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and Large Multimodal Models (LMMs) continue to treat time as a secondary property. This lack of temporal grounding leads to inconsi…
arXiv cs.CV TIER_1 English(EN) · Zelin Zheng, Xinyan Liu, Ruixin Li, Antoni B. Chan, Guorong Li, Qingming Huang, Laiyun Qing · 2026-05-22 04:00

Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding

arXiv:2605.21973v1 Announce Type: new Abstract: Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream, often leading to brittle numerics and inconsistent boundaries. To address this, …

报道来源 [2]

From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning

Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding

相关实体

相关话题