Capability vectors extracted from parameter differences between standard and auxiliary-finetuned VLA models can be merged into pretrained weights to match auxiliary-training performance while reducing computational overhead during adaptation.
Mergevla: Cross-skill model merging toward a generalist vision-language- action agent
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
LifeLong-RFT applies chunking-level on-policy reinforcement learning with Quantized Action Consistency Reward, Continuous Trajectory Alignment Reward, and Format Compliance Reward to fine-tune VLA models, achieving a 22% average success rate gain over supervised fine-tuning on the LIBERO benchmark's
VLA-Pro improves cross-task generalization in vision-language-action models by storing task-specific LoRA adapters as procedural memories and retrieving/fusing them at inference.
citing papers explorer
No citing papers match the current filters.