arXiv (All)
open access
Paraphrase Consensus Is Not Self-Consistency: Instruction Reliance and Robustness in VLA Policies
Vision-language-action (VLA) policies fine-tuned on LIBERO are trained and evaluated on the same ten instruction strings, and rewording the instruction changes base OpenVLA's success by -38.0 points. Test-time prompt ensembling, which improves language models, does not recover this loss in any setti
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
- PathTime-VLA: Path-Time Decoupling for Factorized Post-Training of Vision-Language-Action Policies#1249051
- What Should Robot Policies Learn to Predict? Rethinking Supervision Targets in Vision-Language-Action Learning#1357570
- Does Peer Observation Help? Vision-Sharing Collaboration for Vision-Language Navigation#1357131
- EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies#1131581
- ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills#1249827
Record · ID 1345261
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