Conventional end-to-end (E2E) driving models are effective at generating physically plausible trajectories, but often fail to generalize to long-tail scenarios due to the lack of essential world knowledge to understand and reason about surrounding environments. In contrast, Vision-Language-Action (VLA) models leverage world knowledge to handle challenging cases, but their limited 3D reasoning capability can lead to physically infeasible actions. In this work we introduce DiffVLA++, an enhanced autonomous driving framework that explicitly bridges cognitive reasoning and E2E planning through metric-guided alignment. First, we build a VLA module directly generating semantically grounded driving trajectories. Second, we design an E2E module with a dense trajectory vocabulary that ensures physical feasibility. Third, and most critically, we introduce a metric-guided trajectory scorer that guides and aligns the outputs of the VLA and E2E modules, thereby integrating their complementary strengths. The experiment on the ICCV 2025 Autonomous Grand Challenge leaderboard shows that DiffVLA++ achieves EPDMS of 49.12.
@article{arxiv.2510.17148,
title = {DiffVLA++: Bridging Cognitive Reasoning and End-to-End Driving through Metric-Guided Alignment},
author = {Yu Gao and Anqing Jiang and Yiru Wang and Wang Jijun and Hao Jiang and Zhigang Sun and Heng Yuwen and Wang Shuo and Hao Zhao and Sun Hao},
journal= {arXiv preprint arXiv:2510.17148},
year = {2025}
}