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

• URL: http://arxiv.org/abs/2606.00269v1
• Date: Fri, 29 May 2026 18:59:53 GMT
• Title: Closed-Loop Neural Activation Control in Vision-Language-Action Models
• Abstract summary: We propose a closed-loop framework that replaces static intervention strength with adaptive, time-varying control signals.<n>We instantiate this framework with both PID and reinforcement learning based controllers.<n> Experiments show that residual-STEER achieves more stable concept regulation and a better steering-task success trade-off than fixed-coefficient baselines.
• Score: 19.22723477431829
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving [37.533498955258544]
  We propose a single-pass guidance mechanism that replaces instance-level residuals with class-level latent shifts.<n>We demonstrate that LCS reduces inference latency by approximately 50% while achieving stronger command adherence.
  arXiv  Detail & Related papers  (2026-07-31T19:32:28Z)
• From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation [108.02425846269234]
  controllable image generation has made significant strides by incorporating visual reference conditions.<n>Existing methods predominantly operate as open-loop systems.<n>We propose a novel test-time iterative optimization framework that reformulates reference-consistent generation as a closed-loop dynamic tracking problem.
  arXiv  Detail & Related papers  (2026-07-06T05:36:30Z)
• Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models [26.864668803085888]
  Vision-Language-Action models (VLAs) have demonstrated strong task understanding and generalization in robotic manipulation.<n>We propose an asynchronous semantic-action decoupling framework that separates semantic understanding from action generation.<n>We show that the proposed framework achieves up to 35.6 Hz server-side action- module inference throughput and offers a low-intrusion path to high-frequency closed-loop control.
  arXiv  Detail & Related papers  (2026-06-13T12:49:42Z)
• SteeringDiffusion: A Bottlenecked Activation Control Interface for Diffusion Models [1.9336815376402718]
  SteeringDiffusion is a bottlenecked activation-level control interface for diffusion models.<n>A zero-awared design guarantees exact equivalence to the base model at zero scale.<n>Across experiments on Stable Diffusion1.5 and SDXL, we show that SteeringDiffusion produces smooth and monotonic content-style trade-offs.
  arXiv  Detail & Related papers  (2026-05-03T00:29:10Z)
• Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control [2.752817022620644]
  Inference-time LLM alignment methods offer an alternative to fine-tuning by directly modifying activations during generation.<n>We show that layer-wise dynamics across multiple LLM architectures and scales are well-approximated by locally-linear models.<n>We derive theoretical bounds on setpoint tracking error, enabling formal guarantees on steering performance.
  arXiv  Detail & Related papers  (2026-04-21T03:09:46Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics [81.80010043113445]
  Local weight fine-tuning, LoRA-based adaptation, and activation-based interventions are studied in isolation.<n>We present a unified view that frames these interventions as dynamic weight updates induced by a control signal.<n>Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility.
  arXiv  Detail & Related papers  (2026-02-02T17:04:36Z)
• BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models [34.57464032562792]
  Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos.<n>We present BLURR, a lightweight inference wrapper that can be plugged into existing VLA controllers without retraining or changing model checkpoints.
  arXiv  Detail & Related papers  (2025-12-12T18:30:45Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Activation Steering with a Feedback Controller [4.609594868699996]
  Proportional-Integral-Derivative (PID) Steering is a principled framework that leverages the full PID controller for activation steering in large language models.<n>PID Steering consistently outperforms existing approaches, achieving more robust and reliable behavioral control.
  arXiv  Detail & Related papers  (2025-10-05T18:05:28Z)
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [70.72227437717467]
  Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
  arXiv  Detail & Related papers  (2025-06-15T05:04:17Z)
• Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution [51.83951489847344]
  In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
  arXiv  Detail & Related papers  (2024-04-05T17:58:37Z)
• Optimal PID and Antiwindup Control Design as a Reinforcement Learning Problem [3.131740922192114]
  We focus on the interpretability of DRL control methods. In particular, we view linear fixed-structure controllers as shallow neural networks embedded in the actor-critic framework.
  arXiv  Detail & Related papers  (2020-05-10T01:05:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.