SenseNova-U1.5: Towards Native Unified Visual Intelligence
- URL: http://arxiv.org/abs/2609.11929v1
- Date: Thu, 10 Sep 2026 17:59:55 GMT
- Title: SenseNova-U1.5: Towards Native Unified Visual Intelligence
- Abstract summary: SenseNova-U1.5 is an 8B-MoT native unified multimodal model that understands, reasons about, and generates visual content.<n>We scale its training with carefully curated generation and editing data, improved task formulation, structural prompt enhancement, and native resolutions of up to 4K.<n>We will open-source training code, including supervised fine-tuning, reinforcement learning, and on-policy distillation.
- Score: 100.20348258853939
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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. We strengthen its visual interface through spatially coherent patch reconstruction and scale its training with carefully curated generation and editing data, improved task formulation, structural prompt enhancement, and native resolutions of up to 4K. For post-training, we optimize specialized experts for visual aesthetics, bilingual text rendering, infographic generation, and image editing, and consolidate their capabilities through multi-expert on-policy distillation. Across extensive evaluations, SenseNova-U1.5 largely advances image fidelity, text rendering, complex composition, multi-reference editing, and interleaved generation, while improving instruction following and preserving subject identity, geometry, and unmodified regions. Despite limited exposure to structured formats in its generation data, SenseNova-U1.5 generalizes effectively to long, complex, and structured visual instructions, further proving that multimodal understanding can transfer to visual planning and creation. Together, these findings position native unified modelling as a promising path towards systems that perceive, reason and create within a fully end-to-end framework. We will open-source training code, including supervised fine-tuning, reinforcement learning, and on-policy distillation.
Related papers
- From Dense Prediction to Visual Editing: Structured Supervision for Unified Image and Video Creation [47.1844759979843]
Unified image and video creation requires a model to follow diverse instructions while preserving identity, geometry, and temporal structure from visual context.<n>We formulate depth and surface-normal prediction as image-form denoising targets, using these dense tasks as structured visual supervision within the same creation interface.
arXiv Detail & Related papers (2026-08-13T18:11:45Z) - Vision as Unified Multimodal Generation [73.31482353559736]
SenseNova-Vision is a computer-vision instruction-response corpus spanning text, image, and mixed targets.<n>The model covers a broad range of vision tasks, including detection, OCR, keypoint estimation, segmentation, depth estimation, surface normal prediction, point maps, and camera pose estimation.<n> Experiments show that a single unified model can match leading task-specialized systems across structured visual understanding, dense geometric prediction, segmentation, and multi-view visual geometry.
arXiv Detail & Related papers (2026-07-07T17:58:33Z) - SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture [110.20462227888915]
We introduce SenseNova-U1, a native unified multimodal paradigm built upon NEO-unify.<n>We show two native unified variants, SenseNova-U1-8B-MoT and SenseNova-U1-A3B-MoT, built on dense (8B) and mixture-of-experts (30B-A3B) understanding baselines.<n>We also show detailed model design, data preprocessing, pre-/post-training, and inference strategies to support community research.
arXiv Detail & Related papers (2026-05-12T17:59:58Z) - Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation [68.03746493619285]
We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing.<n>We build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals.<n> Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance.
arXiv Detail & Related papers (2026-05-05T15:49:47Z) - Wan-Image: Pushing the Boundaries of Generative Visual Intelligence [86.08534008471356]
Wan-Image is a unified visual generation system engineered to paradigm-shift image generation models.<n>It is powered by large-scale multi-modal data scaling, a systematic fine-grained annotation engine, and curated reinforcement learning data.<n>Ultimately, Wan-Image revolutionizes visual content creation across e-commerce, entertainment, education, and personal productivity.
arXiv Detail & Related papers (2026-04-21T17:58:58Z) - Factuality Matters: When Image Generation and Editing Meet Structured Visuals [46.627460447235855]
We construct a large-scale dataset of 1.3 million high-quality structured image pairs.<n>We train a unified model that integrates a VLM with FLUX.1 Kontext.<n>A three-stage training curriculum enables progressive feature alignment, knowledge infusion, and reasoning-augmented generation.
arXiv Detail & Related papers (2025-10-06T17:56:55Z) - Unified Multimodal Model as Auto-Encoder [69.38946823657592]
We introduce a paradigm regarding understanding as the encoder (I2T) that compresses images into text, and generation as the decoder (T2I) that reconstructs images from that text.<n>Our empirical results suggest that understanding can largely enhance generation (verified on GenEval), while generation, in turn, notably strengthens fine-grained visual perception.
arXiv Detail & Related papers (2025-09-11T17:57:59Z) - UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation [14.95468978198402]
OpenAI introduced the powerful GPT-4o-Image model, which showcases advanced capabilities in comprehensive image perception and manipulation.<n>Inspired by this insight, we propose UniWorld-V1, a unified generative framework built upon semantic features extracted from powerful large language models.
arXiv Detail & Related papers (2025-06-03T17:59:33Z) - POINTS1.5: Building a Vision-Language Model towards Real World Applications [33.53291443466257]
We introduce a new vision-language model, POINTS1.5, designed to excel in various real-world applications.<n>We replace the original CLIP vision encoder, which had a fixed image resolution, with a NaViT-style vision encoder that supports native dynamic high resolution.<n>We add bilingual support to POINTS1.5, significantly enhancing its capability in Chinese.
arXiv Detail & Related papers (2024-12-11T15:08:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.