paper-with-me

Papers

SenseNova-U1.5: Towards Native Unified Visual Intelligence

2026-09-10 · 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 hf

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.

📄 PDF Abstract BibTeX arXiv:2609.11929

Code (3)

InsomaniacElf/sg-tamil-tts-resources- ★ 1
Tavish9/awesome-daily-AI-arxiv ★ 115
alloevil/AI-Paper-Daily ★ 1

Tasks

Reinforcement LearningInstruction FollowingImage Editing

Similar Papers 제목 키워드 기반

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

2026-05-12 · Haiwen Diao, Penghao Wu, Hanming Deng, Jiahao Wang 외 arxiv

Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipeline…

Scaling Spatial Intelligence with Multimodal Foundation Models

2025-11-17 · Zhongang Cai, Ruisi Wang, Chenyang Gu, Fanyi Pu 외 arxiv

Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence …

Vision as Unified Multimodal Generation

2026-07-07 · Xiaoyang Han, Jianhua Li, Kewang Deng, Zukai Chen 외 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 architectu…

Camera Pose Estimationmultimodal generationDepth EstimationImage Generation

SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning

2025-12-30 · Yong Xien Chng, Tao Hu, Wenwen Tong, Xueheng Li 외 arxiv

While Vision-Language Models (VLMs) can solve complex tasks through agentic reasoning, their capabilities remain largely constrained to text-oriented chain-of-thought or isolated tool invocation. They fail to exhibit the…

Reinforcement LearningVisual ReasoningImage Cropping

VistaHop: Benchmarking Long-Horizon Visual DeepSearch

2026-06-02 · Hang He, Chuhuai Yue, Chengqi Dong, Chengcheng Wan 외 arxiv

Visual DeepSearch tasks require multimodal large language models (MLLMs) to resolve complex visual queries by repeatedly inspecting image regions, grounding reasoning in visual evidence, and connecting fine-grained clues…

Question AnsweringVisual GroundingVisual ReasoningImage Cropping