VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction

• URL: http://arxiv.org/abs/2608.09448v2
• Date: Wed, 12 Aug 2026 10:16:02 GMT
• Title: VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction
• Abstract summary: Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams.<n>We introduce a reliable TTT framework for VLA policies (VANE)<n>On SimplerEnv WidowX, VANE improves average success by $3.2$ percentage points over the corresponding TTT baseline.
• Score: 8.801486222527984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams, but it remains difficult to use reliably in closed-loop manipulation. A shared adaptation space can mix incompatible task corrections, while an online update can alter subsequent actions before its consequences are known. We introduce a reliable TTT framework for VLA policies (VANE). VANE conditions prompt adaptation on the current vision--language context and learns from the future visual consequences of executed actions. Candidate updates are isolated from the live policy, evaluated on subsequent observations, and committed only when supported by future evidence, making adaptation selective and reversible. On SimplerEnv WidowX, VANE improves average success by $3.2$ percentage points over the corresponding TTT baseline. Results on Google Robot further show that deployment-time gains remain task- and embodiment-dependent. Together, these results demonstrate a constrained, evidence-based approach to adapting VLA policies during interaction.

Related papers

• ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models [9.31323513616827]
  We present ICI-VLA, a training and retrieval framework that equips a text-action VLM with few-shot test-time adaptation through in-context demonstrations.<n>ICI-VLA updates its parameters only during offline training; at inference, the policy remains fixed and conditions action generation on retrieved micro-demonstrations.
  arXiv  Detail & Related papers  (2026-09-07T14:55:35Z)
• VLA-Corrector: Stage-Aware Observable State Understanding for Prompt-Based Closed-Loop Recovery of Vision-Language-Action Policies [12.698552476812855]
  Long-horizon robot manipulation with Vision-Language-Action (VLA) policies remains vulnerable to execution-time deviations.<n>We introduce a stage-aware failure verification and Prompt Recovery framework that enables closed-loop correction of a fixed VLA policy.
  arXiv  Detail & Related papers  (2026-09-06T09:50:30Z)
• Action- and Language-Conditioned Video Assessment for Embodied Control [25.788621525752006]
  Vision-based embodied agents executing natural language instructions require feedback mechanisms that assess task progress over complete trajectories.<n>We propose ALVA (Action- and Language-Conditioned Video Assessment), a trajectory evaluator that conditions its assessment on visual observations, the executed action sequence, and the natural language instruction.<n>In simulated 3D household environments, ALVA exhibits a conservative assessment pattern with near-zero false-positive rates.
  arXiv  Detail & Related papers  (2026-08-08T18:05:21Z)
• FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking [51.97839311685636]
  FutureRTC is a plug-and-play adaptation framework that predicts execution-time observations and states for asynchronous VLA control without modifying the underlying policy.<n>We show that FutureRTC achieves robustness to inference delays, resulting in smoother trajectories, faster execution, and consistently higher task success rates.
  arXiv  Detail & Related papers  (2026-07-27T05:10:16Z)
• TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models [49.463896453707065]
  Vision-Language-Action (VLA) models have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time.<n>Recent VLA models suggest that prompts can serve as an efficient interface for steering policy behavior, but existing prompt-based steering typically relies on external guidance.<n>This raises a natural question: can test-time training (TTT) for VLA be achieved by optimizing a prompt, so that the steering interface itself can be learned and adapted from interaction?<n>We address this question with TTT-VLA, a test-time training framework based on Latent Prompt Optimization (LPO)
  arXiv  Detail & Related papers  (2026-06-02T04:10:39Z)
• VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies [58.65913948991329]
  We present VISUALTHINK-VLA, a visual intermediate-reasoning framework for accurate, low-latency VLA policies.<n>Our bootstrapping philosophy is to guide action with effective visual thinking.<n>It bootstraps action prediction through a compact visual-evidence interface that preserves spatial precision while avoiding decoding overhead.
  arXiv  Detail & Related papers  (2026-05-28T14:36:53Z)
• When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs [31.92520697946991]
  Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to faithfully follow language.<n>We show that counterfactual failures are prevalent yet underexplored across state-of-the-art VLAs.<n>We propose Counterfactual Action Guidance (CAG), a simple yet effective dual-branch inference scheme.
  arXiv  Detail & Related papers  (2026-02-19T18:59:20Z)
• ReViP: Reducing False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance [50.05984919728878]
  We present ReViP, a novel VLA framework with Vision-Proprioception Rebalance to enhance visual grounding and robustness under perturbations.<n>Specifically, we use an external VLM as a task-stage observer to extract real-time task-centric visual cues from visual observations.<n>To evaluate false completion, we propose the first False-Completion Benchmark Suite built on LIBERO with controlled settings such as Object-Drop.
  arXiv  Detail & Related papers  (2026-01-23T11:31:07Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• 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)
• Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification [17.948161564138033]
  Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions.<n>But even with a correct textual plan, the generated actions can still miss the intended outcomes in the plan, especially in out-of-distribution scenarios.<n>We formalize this phenomenon as a lack of embodied CoT faithfulness, and introduce a training-free, runtime policy steering method for reasoning-action alignment.
  arXiv  Detail & Related papers  (2025-10-18T00:38:45Z)

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.