Newest papers

Perceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAs

Matteo Cercola, Katie Z Luo, Simone Formentin, Marco Pavone · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28184 · open-access PDF

Hindi

तर्क बढ़ाने वाली दृष्टि-भाषा-एक्शन (VLA) ड्राइविंग मॉडल सुरक्षा महत्वपूर्ण खतरों के बारे में एहसास कर सकते हैं और एहसास कर सकते हैं, लेकिन इस सबूत को सुरक्षित कार्यों में अनुवाद नहीं कर सकते हैं। हम इस विफलता को एक धारणा-एक्शन बाध्यकारी अंतराल के रूप में वर्णन करते हैं: खतरे की जानकारी मॉडल के अंदर उपलब्ध है, लेकिन ट्रैक्चर जनरेटिंग पर पर्याप्त नियंत्रण नहीं करता है।

Machine translation (Meta M2M100); the English original follows.

Abstract

Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evidence into safe actions. We characterize this failure as a perception-action binding gap: hazard information is available inside the model but exerts insufficient control over trajectory generation. Using matched simulated counterfactuals and logged driving replay, we show that in-path hazards are actually encoded in the visual representation, but longitudinal plans are dominated by ego-speed history and respond only weakly to hazard proximity or t

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28184, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange