Ovis embedding models now on Hugging Face, with accompanying paper
AdinaYakup · x · 2026-09-23
Alibaba's ATH MaaS has published the Ovis-Embedding collection on Hugging Face: Ovis-Omni-Embedding-3B (audio-capable), Ovis-VL-Embedding-2B, and Ovis-VL-Embedding-9B, all feature-extraction models. The accompanying paper 'Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings' (arXiv:2609.25165) is also out; the collection sits alongside other Ovis/Marco releases like OvisOCR and Marco-Agent.
Related event: Alibaba Open-Sources Ovis-Embedding, Setting New Multimodal SOTAs(4 posts)→
More from Models
- Dev says Claude Opus 5.5 finds music theory bugs other models missed for weeks — doodlestein · 2026-09-23
- Mystery solved: Opus 5 vs 5.5 chart gap came from thinking levels, not regression — andrew_n_carr · 2026-09-23
- Stop benchmarking LLMs with 3D games, says Abacus.AI CEO — labs fine-tune for it — bindureddy · 2026-09-23
- Opus 5.5 impresses with a hand-crafted Mona Lisa SVG — djcows · 2026-09-23
- MazeBench 3D Spatial Benchmark: Opus 5.5 Hits 6% While GPT-6 Sol and Grok 4.7 Score Just 1% — daniel_mac8 · 2026-09-23
- MazeBench 3D Spatial Reasoning: Opus 5.5 Hits 6% While GPT-6 Sol and Grok 4.7 Manage Just 1% — patience_cave · 2026-09-23