SenseTime releases SenseNova-U1.5, an encoder-free unified multimodal model
Released SenseNova-U1.5, an 8B-MoT native unified multimodal model that handles visual understanding, reasoning and generation in a single architecture, with no encoder and no VAE. It strengthens the visual interface through spatially consistent patch reconstruction, and expands training with curated generation and editing data, improved task formulation, structured prompt enhancement and native resolutions of up to 4K. In post-training, experts for visual aesthetics, bilingual text rendering, infographic generation and image editing are each optimized and then merged through multi-expert on-policy distillation. The company claims large improvements in image fidelity, text rendering, complex composition, multi-reference editing and interleaved generation, and says it will open-source the SFT, RL and on-policy distillation training code.
Why it matters
Shows that a fully end-to-end unified architecture with neither a separate vision encoder nor a VAE has reached practical performance, suggesting that the standard design of unified multimodal models may change.
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2609.11929Added in Week 38, 2026 · See that week