DreamAvoid uses a Dream Trigger, Action Proposer, and Dream Evaluator trained on success/failure/boundary data to let VLA policies avoid critical-phase failures via test-time future dreaming.
Evolve-vla: Test-time training from environment feedback for vision- language-action models.arXiv preprint arXiv:2512.14666
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 4polarities
background 4representative citing papers
T^2VLA is a test-time reinforcement learning framework for VLAs that uses internal confidence to define intrinsic rewards via similarity to high-confidence expert demonstrations and a dual-expert bootstrapping mechanism.
Agentic-VLA enables efficient online adaptation of VLA models, delivering +12.3% on long-horizon tasks, +28.5% in 1-shot learning, and 2.4x faster convergence on LIBERO through three new components.
Anchor-Centric Adaptation escapes the diversity trap by prioritizing repeated demonstrations at core anchors over broad coverage, yielding higher success rates under fixed data budgets in robotic manipulation.
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
Action-state consistency in World Action Models distinguishes successful from failed imagined futures and supports value-free selection of better rollouts via consensus among predictions.
T³VF applies test-time training on natural future-prediction supervision pairs with adaptive filtering to mitigate OOD shifts in VF-VLA models at modest extra inference cost.
FAR combines failure-contrastive preference adaptation with action perturbations for test-time recovery and continual policy improvement, reporting 17.6% and 11.7% success gains over diffusion policies in simulation and real-world manipulation tasks.
citing papers explorer
-
DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
DreamAvoid uses a Dream Trigger, Action Proposer, and Dream Evaluator trained on success/failure/boundary data to let VLA policies avoid critical-phase failures via test-time future dreaming.
-
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
T^2VLA is a test-time reinforcement learning framework for VLAs that uses internal confidence to define intrinsic rewards via similarity to high-confidence expert demonstrations and a dual-expert bootstrapping mechanism.
-
Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Agentic-VLA enables efficient online adaptation of VLA models, delivering +12.3% on long-horizon tasks, +28.5% in 1-shot learning, and 2.4x faster convergence on LIBERO through three new components.
-
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
Anchor-Centric Adaptation escapes the diversity trap by prioritizing repeated demonstrations at core anchors over broad coverage, yielding higher success rates under fixed data budgets in robotic manipulation.
-
PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
-
Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
Action-state consistency in World Action Models distinguishes successful from failed imagined futures and supports value-free selection of better rollouts via consensus among predictions.
-
Test-Time Training for Visual Foresight Vision-Language-Action Models
T³VF applies test-time training on natural future-prediction supervision pairs with adaptive filtering to mitigate OOD shifts in VF-VLA models at modest extra inference cost.
-
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
FAR combines failure-contrastive preference adaptation with action perturbations for test-time recovery and continual policy improvement, reporting 17.6% and 11.7% success gains over diffusion policies in simulation and real-world manipulation tasks.