ROAD-VLA constructs an advantage-perturbed proximal teacher in action space to convert sparse rewards into dense supervision for online VLA adaptation and reports outperformance versus PPO across seven manipulation environments.
Robustvla: Robustness- aware reinforcement post-training for vision-language-action models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
Reflective VLA improves VLA generalization on LIBERO-Plus and LIBERO-Plus-Hard by 5.4 and 4.2 percentage points by conditioning on action consequences instead of reactive single-frame inputs.
PAIR-VLA adds invariance and sensitivity objectives over paired visual variants during PPO fine-tuning of VLA models, yielding 9-16% average gains on ManiSkill3 under distractors, textures, poses, viewpoints, and lighting shifts.
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.
VLA models exhibit joint-dependent success degradation under realistic physical faults, which J-PARC mitigates via latent regime inference and residual action correction.
RoVLA enforces instructional, evolutionary, and observational consistency to improve robustness of VLA policies on manipulation benchmarks and real robots.
VLAMotor exposes VLA failures via distance-aware uncertainty testing and synthesizes agent-planned repair data to fine-tune models, reporting 49.25% success rate gains in simulation and 57.5% on hardware.
citing papers explorer
-
ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models
ROAD-VLA constructs an advantage-perturbed proximal teacher in action space to convert sparse rewards into dense supervision for online VLA adaptation and reports outperformance versus PPO across seven manipulation environments.
-
Reflective VLA: In-Context Action Consequences Make VLAs Generalize
Reflective VLA improves VLA generalization on LIBERO-Plus and LIBERO-Plus-Hard by 5.4 and 4.2 percentage points by conditioning on action consequences instead of reactive single-frame inputs.
-
What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
PAIR-VLA adds invariance and sensitivity objectives over paired visual variants during PPO fine-tuning of VLA models, yielding 9-16% average gains on ManiSkill3 under distractors, textures, poses, viewpoints, and lighting shifts.
-
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.
-
Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults
VLA models exhibit joint-dependent success degradation under realistic physical faults, which J-PARC mitigates via latent regime inference and residual action correction.
-
RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models
RoVLA enforces instructional, evolutionary, and observational consistency to improve robustness of VLA policies on manipulation benchmarks and real robots.
-
VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis
VLAMotor exposes VLA failures via distance-aware uncertainty testing and synthesizes agent-planned repair data to fine-tune models, reporting 49.25% success rate gains in simulation and 57.5% on hardware.
- STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations