Bring Back Language to Actions: Restoring VLM capabilities in VLA Models via Parameter Merging
This story is from 2026-11-18. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2611.18891v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) are obtained by fine-tuning pre-trained Vision-Language Models (VLMs) on robot demonstration data, enabling action prediction from visual observations and language instructions. However, this fine-tuning induces ca…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-18 05:00 · arXiv cs.AI
Bring Back Language to Actions: Restoring VLM capabilities in VLA Models via Parameter Merging