VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use

תקציר מקורי באנגליתarXiv:2608.08477v3 Announce Type: replace Abstract: 25 pages, 1 figure, 10 tables. v3: transplanting a natively-trained visual tower (Qwen2-VL) onto the same frozen decoder takes the failing 8-nibble address field from 0.00 to 0.81 exact, at a coarser token budget than 2x2 tiling, refuting resolution as the operative variable. Second pre-registered field found 63% contaminated, demoted. B6/B7 tool-id remains at floor. Code/checkpoints on HF.