arxiv
PublishedMay 13, 2026 at 4:00 AM
—neutral
ZAYA1-VL-8B Technical Report
Publisher summary· verbatim
arXiv:2605.08560v1 Announce Type: cross Abstract: We present ZAYA1-VL-8B, a compact mixture-of-experts vision-language model built upon our in-house language model, ZAYA1-8B. Despite its compact size, ZAYA1-VL achieves performance competitive with leading base models such as Molmo2-4B and InternVL3.
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivLearning to Discretize: Diffusion-Based Adaptive Mesh with Spectral Guidance8harxivToward Trustworthy Autonomous Science: A Two-Year Community Roadmap8harxivReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams8harxivMirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection8hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗