Episode
Vision as Unified Multimodal Generation
- Podcast
- Daily Paper Cast
- Published
- Jul 9, 2026
- Duration seconds
- 1578
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/b29bc9e3
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/vision-as-unified-multimodal-generation/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/vision-as-unified-multimodal-generation.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 33 | cs.CV Authors: Xiaoyang Han, Jianhua Li, Kewang Deng, Zukai Chen, Xuanke Shi, Sihan Wang, Boxuan Li, Linyan Wang, Siyi Xie, Xin You, Jinsheng Quan, Zhongang Cai, Haiwen Diao, Ziwei Liu, Lei Yang, Dahua Lin, Quan Wang Title: Vision as Unified Multimodal Generation Arxiv: http://arxiv.org/abs/2607.06560v1 Abstract: 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…