IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action Policies

arXiv:2609.15005 · cs.RO, cs.AI · Submitted 2026-09-14 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-14

Updated: 2026-09-14

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Interpretability — 7× in this paper · explained in 15 episodes
• Multimodal Inputs — 7× in this paper · explained in 2 episodes
• Redundancy — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Robustness — 3× in this paper · explained in 5 episodes
• Shapley values — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• VLA Models — 2× in this paper · explained in 3 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation
• Decoding Task Progress from VLA Representations
• Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
• Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies

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