ZAYA1-VL-8B Technical Report
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 InternVL3.5-4B, while surpassing models including Qwen2.5-VL-3B, PLM-3B, and MolmoE-1B across a range of image understanding, reasoning, and counting benchmarks. The architecture incorporates two key innovations: (1) vision-specific LoRA adapters integrated into the LLM to increase modality-specific capacity without increasing the number of experts, and (2) bidirectional attention over image tokens within the LLM to enhance visual understanding. We deta...
| Authors | Hassan Shapourian, Kasra Hejazi, Olabode M. Sule et al. |
|---|---|
| Primary category | cs.CV |
| Published | 8 May 2026 |
| Last updated at source | 8 May 2026 |
Connected in the knowledge graph
- Zyphra/ZAYA1-VL-8BModel · cited by
Models and datasets referencing this paper
- Zyphra/ZAYA1-VL-8BModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.