# Vision as Unified Multimodal Generation

arXiv: https://arxiv.org/abs/2607.06560 · HTML: https://mlsanity.com/paper/2607.06560/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 171 of its 215 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Builds on (most cited first, 30 of 171)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)

## Built on by (most cited first, 7 of 7)

- [InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation](https://mlsanity.com/paper/2609.02004/) (2026)
- [Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States](https://mlsanity.com/paper/2609.04196/) (2026)
- [SegBanana: Steering Unified Multimodal Models into Medical Segmenters](https://mlsanity.com/paper/2609.34235/) (2026)
- [GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed](https://mlsanity.com/paper/2609.39600/) (2026)
- [GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives](https://mlsanity.com/paper/2609.39601/) (2026)
- [IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning](https://mlsanity.com/paper/2610.05342/) (2026)
- [Self-correction Optimization for Interleaved Multimodal Generation](https://mlsanity.com/paper/2610.10400/) (2026)

## Abstract (arXiv)

We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal model, without task-specific architectures. Under this formulation, SenseNova-Vision uses natural-language instructions and optional visual prompts to specify tasks, target regions or views, and decoding conventions, and generates responses as text for symbolic outputs, images for dense spatial predictions, or mixed text-and-image outputs for compositional tasks. To support large-scale training, we convert diverse computer vision annotations into instruction-response examples compatible with these generation spaces, resulting in the SenseNova-Vision Corpus, a computer-vision instruction-response corpus spanning text, image, and mixed targets. Starting from an off-the-shelf pretrained unified multimodal model, SenseNova-Vision is trained primarily on this corpus, with auxiliary multimodal data used as a capability-preserving mixture, and requires no task-specific prediction heads or architectural modifications. The resulting 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, while supporting language-defined variants that combine category, color, region, and other visual cues. 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. These results suggest unified multimodal generation as a scalable route for integrating computer vision capabilities into general-purpose foundation models. The model and corpus are publicly available.