# FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning

arXiv: https://arxiv.org/abs/2509.16445 · HTML: https://mlsanity.com/paper/2509.16445/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2025.

## Built on by (most cited first, 10 of 10)

- [VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory](https://mlsanity.com/paper/2601.08665/) (2026)
- [EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval](https://mlsanity.com/paper/2510.18546/) (2025)
- [Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation](https://mlsanity.com/paper/2605.27582/) (2026)
- [HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness](https://mlsanity.com/paper/2609.15195/) (2026)
- [BREATH-VL: Vision-Language-Guided 6-DoF Bronchoscopy Localization via Semantic-Geometric Fusion](https://mlsanity.com/paper/2601.03713/) (2026)
- [MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation](https://mlsanity.com/paper/2602.05467/) (2026)
- [HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation](https://mlsanity.com/paper/2607.29600/) (2026)
- [LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation](https://mlsanity.com/paper/2608.30935/) (2026)
- [TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios](https://mlsanity.com/paper/2603.29759/) (2026)
- [GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models](https://mlsanity.com/paper/2610.14541/) (2026)

## Abstract (arXiv)

Enabling robotic assistants to navigate complex environments and locate objects described in free-form language is a critical capability for real-world deployment. While foundation models, particularly Vision-Language Models (VLMs), offer powerful semantic understanding, effectively adapting their web-scale knowledge for embodied decision-making remains a key challenge. We present FiLM-Nav (Fine-tuned Language Model for Navigation), an approach that directly fine-tunes pre-trained VLM as the navigation policy. In contrast to methods that use foundation models primarily in a zero-shot manner or for map annotation, FiLM-Nav learns to select the next best exploration frontier by conditioning directly on raw visual trajectory history and the navigation goal. Leveraging targeted simulated embodied experience allows the VLM to ground its powerful pre-trained representations in the specific dynamics and visual patterns relevant to goal-driven navigation. Critically, fine-tuning on a diverse data mixture combining ObjectNav, OVON, ImageNav, and an auxiliary spatial reasoning task proves essential for achieving robustness and broad generalization. FiLM-Nav sets a new state-of-the-art in both SPL and success rate on HM3D ObjectNav among open-vocabulary methods, and sets a state-of-the-art SPL on the challenging HM3D-OVON benchmark, demonstrating strong generalization to unseen object categories. Our work validates that directly fine-tuning VLMs on diverse simulated embodied data is a highly effective pathway towards generalizable and efficient semantic navigation capabilities.