SenseNova-U1.5: Towards Native Unified Visual Intelligence
SenseTime releases SenseNova-U1.5, an 8B-MoT encoder-free multimodal model unifying visual understanding, reasoning, and generation with native 4K resolution.
SenseNova-U1.5 is an 8B mixture-of-transformers multimodal model with an encoder-free, VAE-free architecture that understands, reasons about, and generates visual content at native resolutions up to 4K. Post-training optimizes specialized experts for visual aesthetics, bilingual text rendering, infographic generation, and image editing, consolidated through multi-expert on-policy distillation. Evaluations report gains in image fidelity, text rendering, multi-reference editing, and instruction following. The team plans to open-source training code including supervised fine-tuning, reinforcement learning, and on-policy distillation.
- 8B-MoT encoder-free, VAE-free architecture unifies multimodal understanding and generation
- Specialized experts handle aesthetics, bilingual text rendering, infographics, and image editing
- Multi-expert on-policy distillation consolidates expert capabilities
- Training code for SFT, RL, and distillation will be open-sourced
- Vendors
- SenseTime
- Organizations
- SenseTime
- AI models
- SenseNova-U1.5
From the original article
1 min read at huggingface.co
We launch SenseNova-U1. 5, an 8B-MoT native unified multimodal model that understands, reasons about, and generates visual content within an encoder-free and VAE-free architecture.
By Haiwen Diao, Jiahao Wang, Chenjing Ding · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.