VLS: Steering Pretrained Robot Policies via Vision-Language Models

• URL: http://arxiv.org/abs/2602.03973v1
• Date: Tue, 03 Feb 2026 19:50:16 GMT
• Title: VLS: Steering Pretrained Robot Policies via Vision-Language Models
• Authors: Shuo Liu, Ishneet Sukhvinder Singh, Yiqing Xu, Jiafei Duan, Ranjay Krishna,
• Abstract summary: Vision-Language Steering (VLS) is a training-free framework for inference-time adaptation of frozen generative robot policies.<n>VLS treats adaptation as an inference-time control problem, steering the sampling process of a pretrained diffusion or flow-matching policy.
• Score: 31.189909515514668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a limitation of imitation learning under train-test shifts, where action generation is tightly coupled to training-specific spatial configurations and task specifications. Retraining or fine-tuning to address these failures is costly and conceptually misaligned, as the required behaviors already exist but cannot be selectively adapted at test time. We propose Vision-Language Steering (VLS), a training-free framework for inference-time adaptation of frozen generative robot policies. VLS treats adaptation as an inference-time control problem, steering the sampling process of a pretrained diffusion or flow-matching policy in response to out-of-distribution observation-language inputs without modifying policy parameters. By leveraging vision-language models to synthesize trajectory-differentiable reward functions, VLS guides denoising toward action trajectories that satisfy test-time spatial and task requirements. Across simulation and real-world evaluations, VLS consistently outperforms prior steering methods, achieving a 31% improvement on CALVIN and a 13% gain on LIBERO-PRO. Real-world deployment on a Franka robot further demonstrates robust inference-time adaptation under test-time spatial and semantic shifts. Project page: https://vision-language-steering.github.io/webpage/

Related papers

• When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering [10.01278648231868]
  Policy steering is an emerging way to adapt robot behaviors at deployment-time.<n> Vision-Language Models (VLMs) are promising general-purpose verifiers due to their reasoning capabilities.<n>We propose uncertainty-aware policy steering (UPS), a framework that jointly reasons about semantic task uncertainty and low-level action feasibility.
  arXiv  Detail & Related papers  (2026-02-25T23:23:22Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models [21.133970394496327]
  Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control.<n>Current test-time scaling (TTS) methods require additional training, verifiers, and multiple forward passes, making them impractical for deployment.<n>We propose a simple inference strategy that jointly modulates visual perception and action based on'self-uncertainty'
  arXiv  Detail & Related papers  (2026-02-04T04:48:16Z)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• 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)
• Human-in-the-loop Online Rejection Sampling for Robotic Manipulation [55.99788088622936]
  Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning.<n>Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training.
  arXiv  Detail & Related papers  (2025-10-30T11:53:08Z)
• VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models [49.78447737655287]
  VITA is a zero-shot value function learning method that enhances both capabilities via test-time adaptation.<n>We demonstrate that VITA's zero-shot value estimates can be utilized for reward shaping in offline reinforcement learning.
  arXiv  Detail & Related papers  (2025-06-11T18:05:33Z)
• A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation [30.207690822989292]
  Self-corrected (SC-)VLA framework integrates fast system for directly predicting actions and slow system for reflecting on failed actions.<n>For the fast system, we incorporate parameter-efficient fine-tuning to equip the model with pose prediction capabilities.<n>For the slow system, we propose a Chain-of-Thought training strategy for failure correction, designed to mimic human reflection after a manipulation failure.
  arXiv  Detail & Related papers  (2024-05-27T17:58:48Z)
• Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization [63.75188254377202]
  Deep reinforcement learning algorithms can perform poorly in real-world tasks due to discrepancy between source and target environments. We propose a novel model-free actor-critic algorithm to learn robust policies without modeling the disturbance in advance. Experiments in several robot control tasks demonstrate that SCPO learns robust policies against the disturbance in transition dynamics.
  arXiv  Detail & Related papers  (2021-12-20T13:13:05Z)

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.