NudgeVAD: Language-Nudged End-to-End Driving via FiLM Residuals 事件

NudgeVAD: Language-Nudged End-to-End Driving via FiLM Residuals arXiv:2605.24531v1 Announce Type: new Abstract: Natural-language instructions promise controllable end-to-end driving, but their benefit can be hidden when planners already receive reliable high-level commands. We propose NudgeVAD, a frozen-planner residual framework that uses language as a calibrated nudge to a VAD trajectory. With identity-initialized FiLM and a zero-initialized residual head, NudgeVAD is equivalent to the frozen