arXiv (All)
open access
Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface
Co-training offers a straightforward way to build a multi-task vision-language-action (VLA) policy, but can fall short of the performance achieved by training each task independently. The challenge is to retain these task-specific gains in a multi-task policy without joint post-training. Combining i
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- VLA Foundry: A Unified Framework for Training Vision-Language-Action Models#124125
- IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies#998490
- Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models#1129887
- Dense to MoE Adaptation for Compact Vision Language Action Policies#1149458
- TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies#259503
Record · ID 1117837
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive