{"slug": "imr-iterative-mode-world-weighted-regression-for-multi-agent-trajectory", "title": "IMR: Iterative Mode-World Weighted Regression for Multi-Agent Trajectory Prediction", "summary": "Researchers propose IMR, a novel method for multi-agent trajectory prediction that combines mode-world weighted regression loss and an iterative decoder to improve mode diversity and prediction accuracy. The method ranks first on the Argoverse 2 multi-agent motion forecasting benchmark, addressing safety assessment limitations in automated vehicles.", "body_md": "arXiv:2607.05705v1 Announce Type: cross\nAbstract: Multi-agent motion prediction is essential for automated vehicles to understand the intentions of surrounding vehicles. However, previous prediction-based and anchor-based methods have limitations in mode diversity and prediction accuracy, respectively. These limitations may cause inadequate safety assessments and behavioral deviations in automated vehicles. To address this issue, a mode-world weighted regression loss is proposed to bridge the gap between these features. Specifically, this approach mitigates mode collapse while simultaneously improving world ranking and top-1 confidence. Furthermore, the proposed iterative decoder improves prediction accuracy by recurrently and segmentally generating trajectories. Experimental results show the proposed method ranks first in the Argoverse 2 multi-agent motion forecasting benchmark against other methods.", "url": "https://wpnews.pro/news/imr-iterative-mode-world-weighted-regression-for-multi-agent-trajectory", "canonical_source": "https://www.machinebrief.com/news/imr-iterative-mode-world-weighted-regression-for-multi-agent-vg4f", "published_at": "2026-07-08 04:00:00+00:00", "updated_at": "2026-07-08 04:19:22.339317+00:00", "lang": "en", "topics": ["autonomous-vehicles", "machine-learning", "neural-networks", "computer-vision"], "entities": ["IMR", "Argoverse 2"], "alternates": {"html": "https://wpnews.pro/news/imr-iterative-mode-world-weighted-regression-for-multi-agent-trajectory", "markdown": "https://wpnews.pro/news/imr-iterative-mode-world-weighted-regression-for-multi-agent-trajectory.md", "text": "https://wpnews.pro/news/imr-iterative-mode-world-weighted-regression-for-multi-agent-trajectory.txt", "jsonld": "https://wpnews.pro/news/imr-iterative-mode-world-weighted-regression-for-multi-agent-trajectory.jsonld"}}