aiqbench analysis
Composing insight from the full article — this may take a moment.
Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
arXiv:2605.17204v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and vision-language models do not transfer cleanly to VLAs: outputs are robot actions rather than human-readable tokens, and validating internal changes requires expensive closed-loop rollouts. We propose an event-grounded interpretability pipeline that anchors SAE feature analysis to behavioral events rather than text contexts. We extract keyframes from end-effector trajectories and cluster them within each task using visual, robot-state, and temporal cues. The resulting events guide SAE feature ranking, with optional VLM annotations providing descriptions of the events. To our knowledge, our pipeline is among the first to ground SAE-based VLA analysis in closed-loop behavioral events. Across two simulation architectures and a real-robot study, event-grounded ranking yields the strongest causal effects on OpenVLA and transfers to the continuous action chunks of $\pi_{0.5}$. SAE is a sparse but imperfect intervention basis: usability varies with architecture and intervention site, and aggressive intervention reveals safety and interpretability limits. Overall, event-grounded SAE analysis emerges as a practical starting point for behavior-anchored VLA interpretability, motivating future work on SAE analysis beyond end-effector motion, finer-grained closed-loop evaluation, and safe interventions for high-stakes VLA deployments.
Abstract:Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and vision-language models do not transfer cleanly to VLAs: outputs are robot actions rather than human-readable tokens, and validating internal changes requires expensive closed-loop rollouts. We propose an event-grounded interpretability pipeline that anchors SAE feature analysis to behavioral events rather than text contexts. We extract keyframes from end-effector trajectories and cluster them within each task using visual, robot-state, and temporal cues. The resulting events guide SAE feature ranking, with optional VLM annotations providing descriptions of the events. To our knowledge, our pipeline is among the first to ground SAE-based VLA analysis in closed-loop behavioral events. Across two simulation architectures and a real-robot study, event-grounded ranking yields the strongest causal effects on OpenVLA and transfers to the continuous action chunks of $\pi_{0.5}$. SAE is a sparse but imperfect intervention basis: usability varies with architecture and intervention site, and aggressive intervention reveals safety and interpretability limits. Overall, event-grounded SAE analysis emerges as a practical starting point for behavior-anchored VLA interpretability, motivating future work on SAE analysis beyond end-effector motion, finer-grained closed-loop evaluation, and safe interventions for high-stakes VLA deployments.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2605.17204 [cs.RO]
(or arXiv:2605.17204v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.17204 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 296 words