Closed-Loop Neural Activation Control in Vision-Language-Action Models

Computer Science > Artificial Intelligence [Submitted on 29 May 2026] Closed-Loop Neural Activation Control in Vision-Language-Action Models Abhijith Babu, Ramneet Kaur, Nathaniel D. Bastian, Olivera Kotevska, Susmit Jha, Yanzhao Wu, Sumit Kumar Jha, Anirban Roy Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods use a fixed steering coefficient, effectively operating in open loop. This is poorly suited to embodied control, where task state and concept error evolve over time, often causing overcorrection, oscillation, and reduced task success, especially for temporal behaviors such as speed and smoothness. We propose CTRL-STEER, a closed-loop framework that replaces static intervention strength with adaptive, time-varying control signals. The key idea is to decouple representation from regulation: rather than assuming temporal concepts are directly controlled by individual neurons, we steer along motion-aligned residual directions while a feedback controller adjusts intervention magnitude online. We instantiate this framework with both PID and reinforcement learning based controllers. Experiments with a fine-tuned OpenVLA policy on four LIBERO task suites show that CTRL-STEER achieves more stable concept regulation and a better steering-task success trade-off than fixed-coefficient baselines, without modifying or retraining the base model. Comments: Accepted at the IEEE/CVF CVPR 2026 Workshop on Visual Concepts (VisCon). 25 pages, 8 figures, including supplementary material Subjects: Artificial Intelligence (cs.AI) ACM classes: I.2.9; I.2.10; I.2.6 Cite as: arXiv:2606.00269 [cs.AI]   (or arXiv:2606.00269v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.00269 Focus to learn more Submission history From: Sumit Kumar Jha [view email] [v1] Fri, 29 May 2026 18:59:53 UTC (6,222 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)