analiza aiqbench
This research introduces Anchor-Align, a fine-tuning method for Vision-Language-Action (VLA) models that preserves pretrained visual representations while correcting language-action misalignment. By jointly training on robot observations with discrete motion-direction labels, the approach significantly improves generalization to novel targets and complex bimanual tasks compared to standard behavior cloning. The findings suggest that maintaining semantic grounding during adaptation is critical for robust robotic control in real-world environments.
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
arXiv:2607.13429v2 Announce Type: replace Abstract: Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively overwrites the pretrained representations that support visual and semantic generalization. Co-training on web image-text data, a common remedy, applies language and action losses to separate observations, leaving VLAs with language-action misalignment that standard manipulation benchmarks do not expose. We propose Anchor-Align, which augments BC with two objectives: Vision-Language Anchoring distills layer-wise representations from a frozen VLM copy to prevent this drift, while Language-Action Alignment converts each action target into a discrete motion-direction label and jointly trains language and action prediction on the same robot observation. We conduct real-world evaluations across eight manipulation settings on single-arm xArm7 and bimanual YAM robots, using two VLA architectures with regression and flow-matching action heads. Across these settings, Anchor-Align consistently improves over BC on novel targets, layouts, and motion-sensitive bimanual tasks requiring coordinated control. At scale in simulation, we demonstrate consistent improvements on OOD perturbations, perceptual robustness, and long-horizon control across LIBERO-PRO, LIBERO-Plus, and CALVIN, respectively, suggesting that preserving pretrained representations and effective action learning are not fundamentally at odds. Project page: anchoralignvla.github.io
Abstract:Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively overwrites the pretrained representations that support visual and semantic generalization. Co-training on web image-text data, a common remedy, applies language and action losses to separate observations, leaving VLAs with language-action misalignment that standard manipulation benchmarks do not expose. We propose Anchor-Align, which augments BC with two objectives: Vision-Language Anchoring distills layer-wise representations from a frozen VLM copy to prevent this drift, while Language-Action Alignment converts each action target into a discrete motion-direction label and jointly trains language and action prediction on the same robot observation. We conduct real-world evaluations across eight manipulation settings on single-arm xArm7 and bimanual YAM robots, using two VLA architectures with regression and flow-matching action heads. Across these settings, Anchor-Align consistently improves over BC on novel targets, layouts, and motion-sensitive bimanual tasks requiring coordinated control. At scale in simulation, we demonstrate consistent improvements on OOD perturbations, perceptual robustness, and long-horizon control across LIBERO-PRO, LIBERO-Plus, and CALVIN, respectively, suggesting that preserving pretrained representations and effective action learning are not fundamentally at odds. Project page: this http URL
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2607.13429 [cs.RO]
(or arXiv:2607.13429v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.13429 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 293 cuvinte
Subiecte conexe
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
Models Can't Remember Their Training. Neither Can You.
LessWrong · 19 iul. 2026
HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model
arXiv · 12 oct. 2026
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
LessWrong · 21 sept. 2026