AI & ML
Meaning Reaches Object Choice but Not Completion: Where Is a VLA Vulnerable to Landmark Synonyms?
arXiv cs.RO0 views
arXiv:2611.24076v1 Announce Type: new Abstract: VLA policies are fragile to rewording. Success rates alone cannot say whether a policy fails to choose the object or to complete the task, nor where in the policy to intervene. We study the released GR00T N1.7 on two LIBERO-Spatial tasks differing only in the landmark word telling which of two bowls to take. Synonyms absent from the training instructions send the policy to the bowl they name, unlike made-up words, yet complete 67.6% of one task's closed-loop episodes, against the original word's 100%. Before the connector between the vision-language model and the action generator, replacing only the landmark tokens' vectors with the other landmark's (pasting) sends nearly every episode to the other bowl. After the connector, pasting at the landmark, the remaining instruction, or the image tokens alone rarely moves the choice, but any two do. Hiding the landmark tokens from the action generator after the connector still lowers completion for the synonyms that fall short. Finetuning on diversified landmark words repairs that one task's completion for synonyms absent from finetuning; finetuning on the original instructions does not. Training only the connector on the diversified words suffices, as does copying the connector of a policy fully finetuned on them into one finetuned on the original instructions. An open-loop score on starting frames misses that weights outside the connector also carry part of the repair. For now, on this evidence, robustness to rewording should be judged in closed loop, with actions executed, intervening on both sides of the connector, scoring choice and completion separately.
Source:https://arxiv.org/abs/2611.24076PreviousSemPhys: Semantic-Physical Co-Learning for Humanoid Motion Generation via Differentiable World ModelsNextLost Between Mind, Model Collaboration, and Motion: Understanding and Measuring Cross-Model Action Misalignment in Commercial Robots
Related posts
The draft is not the send
0dev.to Discuss

My First GitHub Issue & My First Forem (DEV.to) Issue 🚀
0dev.to Discuss
Multimodel AI for Business: How to Build a Reliable Video Content Workflow
0dev.to Productivity
Your Thanksgiving flight home is on the busiest travel day of the year
0dev.to Productivity
Audit Week: When Your AI Assistant Knows Your Website Better Than You
0dev.to Productivity

Telegram เตรียม Dictator: AI Agent บน Mac ที่รายงานว่ารันบน Hermes Agent
0dev.to Machine Learning