XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning
Overview
This paper introduces XS-VLA, a staged training framework for compact Vision-Language-Action models that uses coarse-grained spatial distillation to initialize the backbone and latent flow matching conditioned on demonstrations to learn action-space velocity fields. Evaluated on LIBERO benchmarks, XS-VLA achieves an average success rate of 90.25% across two training seeds, outperforming a SmolVLA-0.25B base model trained under the same settings (86.00%). On three Mobile ALOHA tasks, the method increases average strict success from 21.7% to 65.0%. Ablation studies confirm the utility of auxiliary representation initialization and regularized demonstration-conditioned flow learning for improving control performance in compact VLA policies.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · training seeds: 2 other · Basis not reported
“en conditions an action-space velocity field on a demonstration latent, using KL regularization while jointly optimizing the backbone and action modules. The deployed policy contains 243.99M parameters and operates without the teacher or posterior encoder. XS-VLA achieves 90.25% average LIBERO success in each of two training seeds, compared with 86.00% for a SmolVLA-0.25B base trained under our settings. Ablations ex”
Exact source · revision 1Source owner not reported
Reported quantity · Mobile ALOHA tasks: 3 other · Basis not reported
“amine both training stages through matched image pretraining and Huber/MSE controls. On three Mobile ALOHA tasks, average strict success increases from 21.7% to 65.0%. These results demonstrate the control utility of auxiliary representation initialization and regularized demonstration-conditioned flow learning for compact VLA policies”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalXS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning
This paper introduces XS-VLA, a staged training framework for compact Vision-Language-Action models that uses coarse-grained spatial distillation to initialize the backbone and latent flow matching conditioned on demonstrations to learn action-space velocity fields. Evaluated on LIBERO benchmarks, XS-VLA achieves an average success rate of 90.25% across two training seeds, outperforming a SmolVLA-0.25B base model trained under the same settings (86.00%). On three Mobile ALOHA tasks, the method increases average strict success from 21.7% to 65.0%. Ablation studies confirm the utility of auxiliary representation initialization and regularized demonstration-conditioned flow learning for improving control performance in compact VLA policies.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).