Cover Image

Mechanistic interpretability for steering vision-language-action models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Häon, Bear, Stocking, Kaylene, Chuang, Ian, Tomlin, Claire
Format:	Preprint
Published:	2025
Subjects:	Robotics Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security
by: Gibson, Marsalis, et al.
Published: (2024)

Driving pattern interpretation based on action phases clustering
by: Yao, Xue, et al.
Published: (2024)

Gait Switching and Enhanced Stabilization of Walking Robots with Deep Learning-based Reachability: A Case Study on Two-link Walker
by: Xia, Xingpeng, et al.
Published: (2024)

FlySearch: Exploring how vision-language models explore
by: Pardyl, Adam, et al.
Published: (2025)

An Efficient Reachability-Based Framework for Provably Safe Autonomous Navigation in Unknown Environments
by: Bajcsy, Andrea, et al.
Published: (2019)

Training microrobots to swim by a large language model
by: Xu, Zhuoqun, et al.
Published: (2024)

Automatic AI controller that can drive with confidence: steering vehicle with uncertainty knowledge
by: Kumari, Neha, et al.
Published: (2024)

Value-guided action planning with JEPA world models
by: Destrade, Matthieu, et al.
Published: (2025)

Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations
by: Mamedov, Shamil, et al.
Published: (2023)

Using large language models for embodied planning introduces systematic safety risks
by: Zhang, Tao, et al.
Published: (2026)

Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-language Models
by: Li, Mingen, et al.
Published: (2025)

AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps
by: Fan, Liaoyuan, et al.
Published: (2026)

Hierarchical end-to-end autonomous navigation through few-shot waypoint detection
by: Ghafourian, Amin, et al.
Published: (2024)

Training-Free Imitation Learning with Closed-Form Diffusion Policies
by: Mishra, Raghav, et al.
Published: (2026)

Quantization-Free Autoregressive Action Transformer
by: Sheebaelhamd, Ziyad, et al.
Published: (2025)

A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
by: Lei, Yu, et al.
Published: (2026)

Improving planning and MBRL with temporally-extended actions
by: Chatterjee, Palash, et al.
Published: (2025)

Zero-Shot Policy Transfer in Reinforcement Learning using Buckingham's Pi Theorem
by: Pascoa, Francisco, et al.
Published: (2025)

Accelerating Visual-Policy Learning through Parallel Differentiable Simulation
by: You, Haoxiang, et al.
Published: (2025)

A tutorial note on collecting simulated data for vision-language-action models
by: Wu, Heran, et al.
Published: (2025)

FATE-VLA:Failue-aware test generation for vision-language-action models
by: Kanwal, Arusa, et al.
Published: (2026)

The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
by: Chuang, Bing-Cheng, et al.
Published: (2026)

PaRCE: Probabilistic and Reconstruction-based Competency Estimation for CNN-based Image Classification
by: Pohland, Sara, et al.
Published: (2024)

Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
by: Valentin, Romeo, et al.
Published: (2026)

Learning-based adaption of robotic friction models
by: Scholl, Philipp, et al.
Published: (2023)

Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
by: Jiang, Sunshine, et al.
Published: (2025)

Explaining Low Perception Model Competency with High-Competency Counterfactuals
by: Pohland, Sara, et al.
Published: (2025)

Deep hybrid models: infer and plan in a dynamic world
by: Priorelli, Matteo, et al.
Published: (2024)

Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
by: Pan, Chaoyi, et al.
Published: (2025)

Experimental investigation of pose informed reinforcement learning for skid-steered visual navigation
by: Salvi, Ameya, et al.
Published: (2025)

Bird's Eye View Based Pretrained World model for Visual Navigation
by: Lekkala, Kiran, et al.
Published: (2023)

DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion
by: Fan, Yahao, et al.
Published: (2025)

Learning-based Airflow Inertial Odometry for MAVs using Thermal Anemometers in a GPS and vision denied environment
by: Wang, Ze, et al.
Published: (2025)

CGGM: A conditional graph generation model with adaptive sparsity for node anomaly detection in IoT networks
by: Li, Munan, et al.
Published: (2024)

Competency-Aware Planning for Probabilistically Safe Navigation Under Perception Uncertainty
by: Pohland, Sara, et al.
Published: (2024)

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
by: Oota, Subba Reddy, et al.
Published: (2026)

YOLOv10 with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection and trustworthy multimodal AI in computer vision perception
by: Impraimakis, Marios, et al.
Published: (2026)

Deep Neural Networks Tend To Extrapolate Predictably
by: Kang, Katie, et al.
Published: (2023)

ALOHA 2: An Enhanced Low-Cost Hardware for Bimanual Teleoperation
by: ALOHA 2 Team, et al.
Published: (2024)

Mechanistic interpretability of large language models with applications to the financial services industry
by: Golgoon, Ashkan, et al.
Published: (2024)