Democratizando Modelos Generativos de Máscara Texto-para-Imagem com Tokens Unidimensionais Compactos Conscientes do Texto.
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
January 13, 2025
Autores: Dongwon Kim, Ju He, Qihang Yu, Chenglin Yang, Xiaohui Shen, Suha Kwak, Liang-Chieh Chen
cs.AI
Resumo
Os tokenizadores de imagem formam a base dos modelos generativos modernos de texto para imagem, mas são notoriamente difíceis de treinar. Além disso, a maioria dos modelos existentes de texto para imagem dependem de conjuntos de dados privados em grande escala e de alta qualidade, tornando-os desafiadores de replicar. Neste trabalho, apresentamos o Tokenizador 1-Dimensional Baseado em Transformer Consciente de Texto (TA-TiTok), um tokenizador de imagem eficiente e poderoso que pode utilizar tokens 1-dimensionais discretos ou contínuos. O TA-TiTok integra de forma única informações textuais durante a etapa de decodificação do tokenizador (ou seja, de-tokenização), acelerando a convergência e aprimorando o desempenho. O TA-TiTok também se beneficia de um processo de treinamento simplificado, porém eficaz, de um estágio único, eliminando a necessidade da complexa destilação em dois estágios usada nos tokenizadores 1-dimensionais anteriores. Esse design permite uma escalabilidade perfeita para grandes conjuntos de dados. Com base nisso, apresentamos uma família de Modelos Generativos Mascaramentos de Texto para Imagem (MaskGen), treinados exclusivamente em dados abertos, enquanto alcançam desempenho comparável aos modelos treinados em dados privados. Nosso objetivo é disponibilizar tanto os tokenizadores TA-TiTok eficientes e robustos quanto os modelos MaskGen de dados abertos e pesos abertos para promover um acesso mais amplo e democratizar o campo dos modelos generativos mascarados de texto para imagem.
English
Image tokenizers form the foundation of modern text-to-image generative
models but are notoriously difficult to train. Furthermore, most existing
text-to-image models rely on large-scale, high-quality private datasets, making
them challenging to replicate. In this work, we introduce Text-Aware
Transformer-based 1-Dimensional Tokenizer (TA-TiTok), an efficient and powerful
image tokenizer that can utilize either discrete or continuous 1-dimensional
tokens. TA-TiTok uniquely integrates textual information during the tokenizer
decoding stage (i.e., de-tokenization), accelerating convergence and enhancing
performance. TA-TiTok also benefits from a simplified, yet effective, one-stage
training process, eliminating the need for the complex two-stage distillation
used in previous 1-dimensional tokenizers. This design allows for seamless
scalability to large datasets. Building on this, we introduce a family of
text-to-image Masked Generative Models (MaskGen), trained exclusively on open
data while achieving comparable performance to models trained on private data.
We aim to release both the efficient, strong TA-TiTok tokenizers and the
open-data, open-weight MaskGen models to promote broader access and democratize
the field of text-to-image masked generative models.Summary
AI-Generated Summary
DeepSeek-R1: Incentivizando a Capacidade de Raciocínio em LLMs via
Aprendizado por ReforçoDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning
DeepSeek-R1: Incentivizando a Capacidade de Raciocínio em LLMs via
Aprendizado por Reforço
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Qu, Hui Li, Jianzhong Guo, Jiashi Li, Jiawei Wang, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, J. L. Cai, Jiaqi Ni, Jian Liang, Jin Chen, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, Leyi Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R. J. Chen, R. L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, S. S. Li, Shuang Zhou, Shaoqing Wu, Shengfeng Ye, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wanjia Zhao, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W. L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, X. Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xiaowen Sun, Xiaoxiang Wang, Xinnan Song, Xinyi Zhou, Xianzu Wang, Xinxia Shan, Y. K. Li, Y. Q. Wang, Y. X. Wei, Yang Zhang, Yanhong Xu, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y. X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, Zhen Zhang•Jan 22, 2025•3745
Relatório Técnico do Qwen2.5Qwen2.5 Technical Report
Relatório Técnico do Qwen2.5
Qwen2.5 Technical Report
Qwen, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zihan Qiu•Dec 19, 2024•36411
MiniMax-01: Dimensionamento de Modelos de Fundação com Atenção RelâmpagoMiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax-01: Dimensionamento de Modelos de Fundação com Atenção Relâmpago
MiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Chai, Long Xing, Meizhi Ju, Mingyuan Chi, Mozhi Zhang, Peikai Huang, Pengcheng Niu, Pengfei Li, Pengyu Zhao, Qi Yang, Qidi Xu, Qiexiang Wang, Qin Wang, Qiuhui Li, Ruitao Leng, Shengmin Shi, Shuqi Yu, Sichen Li, Songquan Zhu, Tao Huang, Tianrun Liang, Weigao Sun, Weixuan Sun, Weiyu Cheng, Wenkai Li, Xiangjun Song, Xiao Su, Xiaodong Han, Xinjie Zhang, Xinzhu Hou, Xu Min, Xun Zou, Xuyang Shen, Yan Gong, Yingjie Zhu, Yipeng Zhou, Yiran Zhong, Yongyi Hu, Yuanxiang Fan, Yue Yu, Yufeng Yang, Yuhao Li, Yunan Huang, Yunji Li, Yunpeng Huang, Yunzhi Xu, Yuxin Mao, Zehan Li, Zekang Li, Zewei Tao, Zewen Ying, Zhaoyang Cong, Zhen Qin, Zhenhua Fan, Zhihang Yu, Zhuo Jiang, Zijia Wu•Jan 14, 2025•2846