What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior

arXiv:2609.24576 · cs.RO, cs.CV · Submitted 2026-09-21 · Read on arXiv

cs.RO, cs.CV

Submitted: 2026-09-21

Updated: 2026-09-21

Project page: https://utn-air.github.io/vln-interpretability

Terminology

• Steering — 42× in this paper · explained in 2 episodes
• Interpretability — 12× in this paper · explained in 15 episodes
• Activation Steering — 6× in this paper · explained in 4 episodes
• Distribution Shift — 5× in this paper · explained in 5 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Association for Computational Linguistics — 3× in this paper
• Computer Vision and Pattern Recognition — 3× in this paper
• Generalization — 3× in this paper · explained in 13 episodes
• Token Activation Map — 3× in this paper
• Vision-Language Models (VLMs) — 3× in this paper · explained in 6 episodes
• Action Space — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Embeddings — 2× in this paper · explained in 2 episodes
• Integrated Gradients — 2× in this paper
• Interventional Significance Score — 2× in this paper
• Activation Addition — 1× in this paper · explained in 1 episode
• Adaptive Reasoning — 1× in this paper · explained in 2 episodes
• Causal Understanding — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Modern Vision-Language Navigation — 1× in this paper
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes
• TRAJECTORIES WITH ZERO ISS SCORES — 1× in this paper
• Task Decomposition — 1× in this paper · explained in 2 episodes

Sources

• Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation
• ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
• Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
• VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
• Steering Language Models With Activation Engineering
• Representation Engineering: A Top-Down Approach to AI Transparency
• Observing and Controlling Features in Vision-Language-Action Models
• Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving