PaperActive

SenseNova-U1.5: Towards Native Unified Visual Intelligence

arxiv.org/abs/2609.11929

quality81

Updated 5 h ago · first seen 11 Sept 2026

paper_01M294H2N5RNFQDAHHFE1QJJEA

Published: 11 Sept 2026; T1 · 5 h ago
arXiv: 2609.11929; T1 · 5 h ago
Category: cs.CV; T1 · 5 h ago

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.

Authors 65

Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu, Zhengqi Bai, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Bo Yang, Chen Feng, Chengguang Lv, Guangjia Liu, Guanlin Wang, Hanyu Zhang, Haojia Yu, Hongcan Xiao, Hongli Wang, Huan Wu, Huaping Zhong, Jian Fang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jing Zuo, Jingcheng Ni, Junxiang Xu, Linjun Dai, Mutian Xu, Peishen Yan, Penghao Wu, Ruijie Mao, Ruisi Wang, Shihao Bai, Shuang Yang, Shuya Yang, Shuyan Zheng, Silei Wu, Siying Li, Tao Chu, Tianbo Zhong, Tongxi Zhou, Weichao Luo, Weichen Fan, Wenhao Jia, Wenjie Gao, Xiangli Kong, Yan Li, Yang Yong, Zimo Wen, Zixuan Qian, Wenxiu Sun, Ruihao Gong, Quan Wang, Lewei Lu, Lei Yang, Ziwei Liu, Dahua Lin

Specification

Official page: arxiv.org/abs/2609.11929
Source:arXiv (Atom API + RSS)T1observed 5 h agohigh
Arxiv announce type: new
Source:arXiv (Atom API + RSS)T1observed 5 h agohigh
arXiv id: 2609.11929
Source:arXiv (Atom API + RSS)T1observed 5 h agohigh
Categories: cs.CV
Source:arXiv (Atom API + RSS)T1observed 5 h agohigh
Hf paper url: https://huggingface.co/papers/2609.11929
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
Hf comments: 1
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
Upvotes: 128
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
PDF: arxiv.org/pdf/2609.11929
Source:arXiv (Atom API + RSS)T1observed 5 h agohigh
Primary category: cs.CV
Source:arXiv (Atom API + RSS)T1observed 5 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 5 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

Source tiers

T1T29 / 3

Freshest observation

5 h ago

Conflicts

4 flagged

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

16 claims · 12 properties4 conflicting

Official pageofficial_url1

Claim history for Official page
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/abs/2609.11929	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Abstractabstract1

Claim history for Abstract
Value	Valid from → to	Status	Source	Confidence	Extractor
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.	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Arxiv announce typearxiv_announce_type1

Claim history for Arxiv announce type
Value	Valid from → to	Status	Source	Confidence	Extractor
new	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

arXiv idarxiv_id1

Claim history for arXiv id
Value	Valid from → to	Status	Source	Confidence	Extractor
2609.11929	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Authorsauthors3conflicting claims

Claim history for Authors
Value	Valid from → to	Status	Source	Confidence	Extractor
Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu, Zhengqi Bai, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Bo Yang, Chen Feng, Chengguang Lv, Guangjia Liu, Guanlin Wang, Hanyu Zhang, Haojia Yu, Hongcan Xiao, Hongli Wang, Huan Wu, Huaping Zhong, Jian Fang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jing Zuo, Jingcheng Ni, Junxiang Xu, Linjun Dai, Mutian Xu, Peishen Yan, Penghao Wu, Ruijie Mao, Ruisi Wang, Shihao Bai, Shuang Yang, Shuya Yang, Shuyan Zheng, Silei Wu, Siying Li, Tao Chu, Tianbo Zhong, Tongxi Zhou, Weichao Luo	11 Sept 2026 21:12 UTC → current	conflicting	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu, Zhengqi Bai, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Bo Yang, Chen Feng, Chengguang Lv, Guangjia Liu, Guanlin Wang, Hanyu Zhang, Haojia Yu, Hongcan Xiao, Hongli Wang, Huan Wu, Huaping Zhong, Jian Fang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jing Zuo, Jingcheng Ni, Junxiang Xu, Linjun Dai, Mutian Xu, Peishen Yan, Penghao Wu, Ruijie Mao, Ruisi Wang, Shihao Bai, Shuang Yang, Shuya Yang, Shuyan Zheng, Silei Wu, Siying Li, Tao Chu, Tianbo Zhong, Tongxi Zhou, Weichao Luo	11 Sept 2026 21:10 UTC → current	conflicting	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu, Zhengqi Bai, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Bo Yang, Chen Feng, Chengguang Lv, Guangjia Liu, Guanlin Wang, Hanyu Zhang, Haojia Yu, Hongcan Xiao, Hongli Wang, Huan Wu, Huaping Zhong, Jian Fang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jing Zuo, Jingcheng Ni, Junxiang Xu, Linjun Dai, Mutian Xu, Peishen Yan, Penghao Wu, Ruijie Mao, Ruisi Wang, Shihao Bai, Shuang Yang, Shuya Yang, Shuyan Zheng, Silei Wu, Siying Li, Tao Chu, Tianbo Zhong, Tongxi Zhou, Weichao Luo, Weichen Fan, Wenhao Jia, Wenjie Gao, Xiangli Kong, Yan Li, Yang Yong, Zimo Wen, Zixuan Qian, Wenxiu Sun, Ruihao Gong, Quan Wang, Lewei Lu, Lei Yang, Ziwei Liu, Dahua Lin	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	conflicted	deterministic

Categoriescategories1

Claim history for Categories
Value	Valid from → to	Status	Source	Confidence	Extractor
cs.CV	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Hf paper urlhf_paper_url1

Claim history for Hf paper url
Value	Valid from → to	Status	Source	Confidence	Extractor
https://huggingface.co/papers/2609.11929	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hf commentsmetric.hf_comments1

Claim history for Hf comments
Value	Valid from → to	Status	Source	Confidence	Extractor
1	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Upvotesmetric.upvotes1

Claim history for Upvotes
Value	Valid from → to	Status	Source	Confidence	Extractor
128	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

PDFpdf_url1

Claim history for PDF
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/pdf/2609.11929	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Primary categoryprimary_category1

Claim history for Primary category
Value	Valid from → to	Status	Source	Confidence	Extractor
cs.CV	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Publishedpublished_at3conflicting claims

Claim history for Published
Value	Valid from → to	Status	Source	Confidence	Extractor
10 Sept 2026	11 Sept 2026 21:12 UTC → current	conflicting	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
10 Sept 2026	11 Sept 2026 21:10 UTC → current	conflicting	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
11 Sept 2026	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	conflicted	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CV	feed	T1· Official	5 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/papers	listing	T2· Quality secondary	5 h ago	2

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.