中文
相关论文

相关论文: UniGame: Turning a Unified Multimodal Model Into I…

200 篇论文

Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Zihan Su , Hongyang Wei , Kangrui Cen , Yong Wang , Guanhua Chen , Chun Yuan , Xiangxiang Chu

While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage such internal knowledge for high-quality generation. We formalize this discrepancy…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Ruiyan Han , Zhen Fang , XinYu Sun , Yuchen Ma , Ziheng Wang , Yu Zeng , Zehui Chen , Lin Chen , Wenxuan Huang , Wei-Jie Xu , Yi Cao , Feng Zhao

Unified Multimodal Models (UMMs) built on shared autoregressive (AR) transformers are attractive for their architectural simplicity. However, we identify a critical limitation: when trained on multimodal inputs, modality-shared transformers…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Jitai Hao , Hao Liu , Xinyan Xiao , Qiang Huang , Jun Yu

Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs…

人工智能 · 计算机科学 2026-05-21 Yinyi Luo , Wenwen Wang , Hayes Bai , Hongyu Zhu , Hao Chen , Pan He , Marios Savvides , Sharon Li , Jindong Wang

Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture. However, it remains underexplored how to effectively coordinate these two capabilities for more effective and efficient reasoning.…

多媒体 · 计算机科学 2026-05-13 Hayes Bai , Yinyi Luo , Wenwen Wang , Qingsong Wen , Jindong Wang

Recent advances in 3D vision have led to specialized models for either 3D understanding (e.g., shape classification, segmentation, reconstruction) or 3D generation (e.g., synthesis, completion, and editing). However, these tasks are often…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Peng Huang , Yifeng Chen , Zeyu Zhang , Hao Tang

Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-image (T2I) tasks. Despite their theoretical promise, a…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Jiadong Pan , Liang Li , Yuxin Peng , Yu-Ming Tang , Shuohuan Wang , Yu Sun , Hua Wu , Qingming Huang , Haifeng Wang

Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Zimo Wen , Boxiu Li , Wanbo Zhang , Junxiang Lei , Xiaoyu Chen , Yijia Fan , Qi Zhang , Yujiang Wang , Lili Qiu , Bo Li , Ziwei Liu , Caihua Shan , Yifan Yang , Yifei Shen

Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defenses include Barrage of…

机器学习 · 计算机科学 2023-05-02 Ethan Rathbun , Kaleel Mahmood , Sohaib Ahmad , Caiwen Ding , Marten van Dijk

Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work,…

计算机视觉与模式识别 · 计算机科学 2025-06-23 Teng Li , Quanfeng Lu , Lirui Zhao , Hao Li , Xizhou Zhu , Yu Qiao , Jun Zhang , Wenqi Shao

Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Yinyi Luo , Wenwen Wang , Hayes Bai , Marios Savvides , Jindong Wang

In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, development, these two fields have evolved distinct architectural paradigms: the…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Yanran Zhang , Wenzhao Zheng , Yifei Li , Bingyao Yu , Yu Zheng , Lei Chen , Jiwen Lu , Jie Zhou

Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token-level alignment via supervised fine-tuning, which fails to…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Zijun Shen , Sihan Yang , Ruichuan An , Ziyu Guo , Hao Liang , Ming Lu , Renrui Zhang , Wentao Zhang

Game UI development is essential to the game industry. However, the traditional workflow requires substantial manual effort to integrate pairwise UI and UX designs into a cohesive game user interface (GameUI). The inconsistency between the…

人机交互 · 计算机科学 2026-01-28 Zhongliang Tang , Qingrong Cheng , Mengchen Tan , Yongxiang Zhang , Fei Xia

This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that adversarial…

机器学习 · 计算机科学 2021-11-10 Jie Ren , Die Zhang , Yisen Wang , Lu Chen , Zhanpeng Zhou , Yiting Chen , Xu Cheng , Xin Wang , Meng Zhou , Jie Shi , Quanshi Zhang

Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Kai Zou , Ziqi Huang , Yuhao Dong , Shulin Tian , Dian Zheng , Hongbo Liu , Jingwen He , Bin Liu , Yu Qiao , Ziwei Liu

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations are truly aligned across modalities. To investigate this…

计算与语言 · 计算机科学 2026-04-08 Cheng Yang , Chufan Shi , Bo Shui , Yaokang Wu , Muzi Tao , Huijuan Wang , Ivan Yee Lee , Yong Liu , Xuezhe Ma , Taylor Berg-Kirkpatrick

This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i.e.} the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that…

机器学习 · 计算机科学 2021-11-09 Jie Ren , Die Zhang , Yisen Wang , Lu Chen , Zhanpeng Zhou , Yiting Chen , Xu Cheng , Xin Wang , Meng Zhou , Jie Shi , Quanshi Zhang

Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. However, evaluations of unified multimodal models (UMMs) remain decoupled, assessing their understanding and generation…

人工智能 · 计算机科学 2025-12-22 Kai Liu , Leyang Chen , Wenbo Li , Zhikai Chen , Zhixin Wang , Renjing Pei , Linghe Kong , Yulun Zhang
‹ 上一页 1 2 3 10 下一页 ›