# NudgeVAD: Language-Nudged End-to-End Driving via FiLM Residuals Source: [NudgeVAD: Language-Nudged End-to-End Driving via FiLM Residuals]() Collection index: [llms.txt]() Data updated: 2026-05-27T05:00:05.520Z Authors: Chieh-Chi Yang, Yu-Hsiang Chen, Yi-Ting Chen Published: 2026-05-23T11:51:25.000Z ## 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 planner at initialization, so learned deviations arise only from language-conditioned residuals. We evaluate NudgeVAD along a command-reliability axis. With reliable commands, language improves the initial planner but becomes nearly redundant once compared against VAD-FT (UNCOND), a compute-matched VAD model fine-tuned without language. With random commands, however, language becomes essential: detaching text degrades ADE6s to 3.166 m, while NudgeVAD with text recovers 2.806 m and outperforms VAD-FT (UNCOND) by 0.312 m. These results show that language is not universally additive; it is most valuable when the categorical command channel is unreliable. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Trajectory Prediction on doScenes Reliable commands](): Trajectory Prediction; doScenes Reliable commands; ADE: 2.726. - [Trajectory Prediction on doScenes Random commands](): Trajectory Prediction; doScenes Random commands; ADE: 2.806. ## Original sources and implementation [Original paper]() [PDF]()