arXiv (All)
open access
Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners
Embodied vision-language models (VLMs) are increasingly deployed as high-level planners for robots because they generalize across diverse environments. However, this requires their safety alignment to also hold in unseen environments. Existing red-teaming assumes an adversary who optimizes the promp
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
- Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners#1136783
- Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena#1155789
- CrossSafe: Towards Cross-Embodiment Latent Safety Filters#1076640
- ConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts#1115748
- RedVLA: Physical Red Teaming for Vision-Language-Action Models#927294
Record · ID 1143938
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