arXiv (All)
open access
TokenPB: Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
Test-time sampling can improve Vision-Language-Action (VLA) policies, but only if the model can efficiently select a good action from multiple candidates. Prior work often relies on separately trained external verifiers, adding extra models and inference overhead. We propose \textbf{Token Probabilit
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
- Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors#1326806
- IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action Policies#1084904
- Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies#971554
- Beyond Actions: Learning Future Operation Targets for Vision-Language-Action Models#1297564
- Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies#1013736
Record · ID 1327349
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