Eric Liang, Alan Luo, Kaiwen Yuan · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29196 · open-access PDF
Kemajuan baru-baru ini dalam Visual-Language Models (VLM) memungkinkan grounding visual end-to-end melalui prompts bahasa dan generative decoding, menunjukkan kemampuan deteksi nol-shot dan open-vocabulary yang sangat ditingkatkan. Akibatnya, VLM dengan cepat diimplementasikan di tepi dalam sistem dunia nyata yang kritis terhadap keamanan. Namun, ketahanan lawan fisik dari VLM tepi belum secara sistematis dipelajari, dan perbedaan fundamental dalam output dengan detektor objek modern menciptakan tantangan metodologis untuk evaluasi yang adil.
Machine translation (Meta M2M100); the English original follows.
Recent advancements in Vision-Language Models (VLMs) enable end-to-end visual grounding via language prompts and generative decoding, demonstrating largely improved zero-shot and open-vocabulary detection capabilities. As a result, VLMs are rapidly being deployed at the edge in safety-critical real-world systems. However, the physical adversarial robustness of edge VLMs has not been systematically studied, and the fundamental differences in output with modern object detectors create methodological challenges for fair evaluation. To compare the two families directly, we evaluate every selected
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29196, 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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange