MiniMax

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

MiniMax-M2系列：小激活释放最大现实智能

Aili Chen, Aonian Li, Baichuan Zhou, Bangwei Gong, Binyang Jiang, Boji Dan, Changhao Zhang, Changqing Yu, Chao Wang, Cheng Ma, Cheng Zhong, Cheng Zhu, Chengjun Xiao, Chengyi Yang, Chengyu Du, Chenyang Zhang, Chi Zhang, Chuangyi Huang, Chunhao Zhang, Chunhui Du, Chunyu Zhao, Congchao Guo, Da Chen, Deming Ding, Dianjun Sun, Dong Li, Dongyu Zhang, Enhui Yang, Fei Yu, Guang Zheng, Guodong Zheng, Guohong Li, Haichao Zhu, Haigang Zhou, Haimo Zhang, Han Ding, Hao Zhang, Haohai Sun, Haolin Lyu, Haonan Lu, Haoyu Wang, Huajie Shi, Huiyang Li, Jiacheng Chen, Jian Zhang, Jiaqi Zhuang, Jiaren Cai, Jiaxin Pan, Jiayao Li, Jiayuan Song, Jichuan Zhang, Jie Wang, Jihao Gu, Jin Zhu, Jingwei Dong, Jingyang Li, Jingyu Zhang, Jingze Zhuang, Jinhao Tian, Jinli Liu, Jinyi Hu, Jun Tao, Jun Zhang, Junbin Ruan, Junhao Xu, Junjie Yan, Junteng Liu, Junxian He, Kang Xu, Ke Ji, Ke Yang, Kecheng Xiao, Keyu Duan, Keyu Li, Le Han, Letian Ruan, Li Yuan, Lianfei Yu, Liheng Feng, Lijie Mo, Lin Li, Linge Du, Lingye Bao, Lingyu Yang, Lingyuan Zhou, Loki, Lu Chen, Lunbin Zeng, Ming Li, Ming Zhong, Mingliang Tao, Mingyuan Chi, Mujie Lin, Nan Hu, Ningxin Chen, Peiyin Zhu, Peng Gao, Pengcheng Gao, Pengfei Li, Penglin Li, Pengyu Zhao, Qibin Ren, Qibing Ren, Qidi Xu, Qihan Ren, Qile Li, Qin Wang, Quanliang Chen, Qunhong Zeng, Rong Tian, Rongxin Guo, Rui Dong, Ruitao Leng, Ruize Zhang, Shanqi Liu, Shaoxiang Chen, Shaoyu Chen, Sheng Jia, Shun Yao, Shuoran Zhao, Shuqi Yu, Sichen Li, Sicheng Pan, Songquan Zhu, Tengfei Li, Tian Xie, Tiancheng Qin, Tianle Li, Tianrun Liang, Wei Liu, Weiqi Xu, Weitao Li, Weixiang Chen, Weiyu Cheng, Weiyu Zhang, Wenhu Chen, Wenqian Zhao, Xiancai Chen, Xiangjun Song, Xiangyuan Wang, Xianzhen Luo, Xiao Luo, Xiao Su, Xiaobo Li, Xiaodong Han, Xiaojie Wu, Xihao Song, Xingyi Han, Xinyu Guan, Xuan Lu, Xun Zou, Xunhao Lai, Xutong Li, Xuyang Shen, Yan Gong, Yan Ma, Yang Jiao, Yang Wang, Yang Xu, Yangsen Wang, Ye Tang, Yicheng Chen, Yihang Wang, Yinran Qiu, Yiqi Shi, Yiting Guo, Yiwen Huang, Yixuan Wang, Yongyi Hu, Yu Gao, Yu Zhang, Yuan Li, Yuanxiang Ying, Yuanzhen Zhang, Yubo Wang, Yuchen Song, Yufeng Yang, Yuhang Meng, Yuhang Miao, Yuhao Li, Yujie Liu, Yulin Hu, Yunan Huang, Yunji Li, Yunyi Huang, Yusen Zhang, Yusu Hong, Yutao Xie, Yutong Zhang, Yuwen Liao, Yuxuan Shi, Yuze Wenren, Zebin Li, Zehan Li, Zejian Luo, Zeyu Jin, Zeyuan Sun, Zhanpeng Zhou, Zhaochen Su, Zhendong Li, Zhengmao Zhu, Zhengyuan Peng, Zhenhua Fan, Zhi Zhang, Zhichao Xu, Zhiheng Lv, Zhikang Xu, Zhitao He, Zhiwei He, Zhongyuan Li, Zibo Gao, Zijia Wu, Zijian Song, Zijian Zhou, Zijun Sun, Zishan Huang, Ziying Chen, Ziyue Ge

机构 * MiniMax 纠错

AI总结 提出MiniMax-M2系列混合专家语言模型，通过小激活参数实现前沿性能，核心包括智能体驱动数据管道、可扩展强化学习系统Forge及自进化检查点M2.7。

Comments Technical Report. 35 pages, 10 figures, 4 tables

MiniMax Sparse Attention

MiniMax 稀疏注意力

Xunhao Lai, Weiqi Xu, Yufeng Yang, Qiaorui Chen, Yang Xu, Lunbin Zeng, Xiaolong Li, Haohai Sun, Haichao Zhu, Vito Zhang, Jinkai Hu, Jiayao Li, Rui Gao, Zekun Li, Songquan Zhu, Jingkai Zhou, Pengyu Zhao

机构 * MiniMax ； Peking University（北京大学） ； NVIDIA（英伟达） ； Zhejiang University（浙江大学） ； Huazhong University of Science and Technology（华中科技大学） 纠错

AI总结 提出 MiniMax 稀疏注意力（MSA），一种基于分组查询注意力的块级稀疏注意力机制，通过轻量索引分支选择 Top-k 键值块，实现高效长上下文处理，在 109B 模型上以 1M 上下文减少 28.4 倍注意力计算，并带来 14.2 倍预填充和 7.6 倍解码加速。

Comments 30 pages, 14 figures

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

MaxProof: 通过生成-验证器强化学习与群体级测试时扩展实现数学证明规模化

Jiacheng Chen, Xinyu Zhang, Shunkai Zhang, Yanmohan Wang, Lin Li, Tiancheng Qin, Qin Wang, Zhengmao Zhu, Tianle Li, Jingyang Li, Zehan Li, Binyang Jiang, Jin Zhu, Han Ding, Fei Yu, Chenyu Du, Zijian Song, Jiayuan Song, Zhi Zhang, Yunan Huang, Weiyu Cheng, Pengyu Zhao, Yu Cheng

机构 * MiniMax ； The Chinese University of Hong Kong（香港中文大学） ； Fudan University（复旦大学） ； Peking University（北京大学） ； Tsinghua University（清华大学） 纠错

AI总结 提出MaxProof框架，结合生成-验证器强化学习与群体级测试时扩展，在MiniMax-M3系列上实现竞赛级数学证明，在IMO 2025和USAMO 2026上超越人类金牌阈值。

ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison

ClaimDiff-RL: 通过视觉声明比较进行细粒度描述强化学习

Tianle Li, Xuyang Shen, Yan Ma, Rongxin Guo, Shaoxiang Chen, Jiacheng Chen, Haochen Wang, Hongyang Tang, Yucong Zhou, Yu Cheng

机构 * The Chinese University of Hong Kong（香港中文大学） ； MiniMax 纠错

AI总结 提出ClaimDiff-RL框架，利用原子声明差异作为奖励单元，通过多模态判断器枚举视觉差异并分配错误类型和严重程度，以解决长描述强化学习中事实性与覆盖度的权衡问题。

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

CORAL：迈向自主多智能体进化以实现开放性发现

Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li, Cathy Wu, Bryan Kian Hsiang Low, Jinhua Zhao, Paul Pu Liang

机构 * MIT（麻省理工学院） ； NUS（新加坡国立大学） ； MiniMax ； McGill（麦吉尔大学） ； Stanford（斯坦福大学） ； SambaNova ； Meta ； Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工联合研究技术联盟） ； Amazon（亚马逊） ； Microsoft（微软） 纠错

AI总结 本文提出CORAL框架，通过自主多智能体进化方法，实现了在开放性问题上的发现，展示了智能体自主性和多智能体进化对提升开放性发现的显著效果。

HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing

HER：面向大语言模型角色扮演的人类级推理与强化学习

Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding, Pengyu Zhao, Yanghua Xiao

机构 * Fudan University（复旦大学） ； MiniMax 纠错

AI总结 本文提出HER框架，通过双层推理和人类对齐的奖励模型，提升大语言模型在角色扮演中的认知模拟能力，实验表明其在CoSER和Minimax Role-Play Bench上显著优于基线模型。

Comments Findings of ACL, 2026

SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning

SpatialImaginer: 向空间推理的自适应视觉想象迈进

Yian Li, Yang Jiao, Bin Zhu, Tianwen Qian, Shaoxiang Chen, Jingjing Chen, Yu-Gang Jiang

机构 * College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院） ； School of Computing and Information Systems, Singapore Management University（新加坡管理大学 computing 与信息学院） ； School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院） ； MiniMax ； Institute of Trustworthy Embodied Al, Fudan University（复旦大学可信具身人工智能研究院） 纠错

AI总结 本文提出SpatialImaginer框架，通过结合文本推理与视觉想象，解决多模态大语言模型在空间推理中的鲁棒性问题，实验显示其在复杂空间任务中表现优异。

Towards Scalable Pre-training of Visual Tokenizers for Generation

面向生成任务的视觉分词器可扩展预训练

Jingfeng Yao, Yuda Song, Yucong Zhou, Xinggang Wang

机构 * Huazhong University of Science and Technology（华中科技大学） ； MiniMax 纠错

AI总结 VTP通过联合优化图像-文本对比、自监督和重建损失，提升视觉分词器的生成性能和扩展性。

Comments Our pre-trained models are available at https://github.com/MiniMax-AI/VTP

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding

OctoBench：面向仓库基础代理编程的支架意识指令遵循基准测试

Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui

机构 * Fudan University（复旦大学） ； MiniMax ； Peking University（北京大学） 纠错

AI总结 OctoBench通过评估仓库基础代理编程中的支架意识指令遵循能力，揭示了任务解决与合规性之间的差距，推动更高效的编码代理发展。

ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning

ControlThinker: 通过视觉推理揭示潜在语义以实现可控图像生成

Feng Han, Yang Jiao, Shaoxiang Chen, Junhao Xu, Jingjing Chen, Yu-Gang Jiang

机构 * Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（上海智能信息处理关键实验室，复旦大学计算机学院） ； Shanghai Collaborative Innovation Center on Intelligent Visual Computing（上海智能视觉计算协同创新中心） ； MiniMax 纠错

AI总结 ControlThinker通过视觉推理挖掘潜在语义，提升可控图像生成的语义一致性和视觉质量。

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

MiniMax, :, Aili Chen, Aonian Li, Bangwei Gong, Binyang Jiang, Bo Fei, Bo Yang, Boji Shan, Changqing Yu, Chao Wang, Cheng Zhu, Chengjun Xiao, Chengyu Du, Chi Zhang, Chu Qiao, Chunhao Zhang, Chunhui Du, Congchao Guo, Da Chen, Deming Ding, Dianjun Sun, Dong Li, Enwei Jiao, Haigang Zhou, Haimo Zhang, Han Ding, Haohai Sun, Haoyu Feng, Huaiguang Cai, Haichao Zhu, Jian Sun, Jiaqi Zhuang, Jiaren Cai, Jiayuan Song, Jin Zhu, Jingyang Li, Jinhao Tian, Jinli Liu, Junhao Xu, Junjie Yan, Junteng Liu, Junxian He, Kaiyi Feng, Ke Yang, Kecheng Xiao, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Li, Lin Zheng, Linge Du, Lingyu Yang, Lunbin Zeng, Minghui Yu, Mingliang Tao, Mingyuan Chi, Mozhi Zhang, Mujie Lin, Nan Hu, Nongyu Di, Peng Gao, Pengfei Li, Pengyu Zhao, Qibing Ren, Qidi Xu, Qile Li, Qin Wang, Rong Tian, Ruitao Leng, Shaoxiang Chen, Shaoyu Chen, Shengmin Shi, Shitong Weng, Shuchang Guan, Shuqi Yu, Sichen Li, Songquan Zhu, Tengfei Li, Tianchi Cai, Tianrun Liang, Weiyu Cheng, Weize Kong, Wenkai Li, Xiancai Chen, Xiangjun Song, Xiao Luo, Xiao Su, Xiaobo Li, Xiaodong Han, Xinzhu Hou, Xuan Lu, Xun Zou, Xuyang Shen, Yan Gong, Yan Ma, Yang Wang, Yiqi Shi, Yiran Zhong, Yonghong Duan, Yongxiang Fu, Yongyi Hu, Yu Gao, Yuanxiang Fan, Yufeng Yang, Yuhao Li, Yulin Hu, Yunan Huang, Yunji Li, Yunzhi Xu, Yuxin Mao, Yuxuan Shi, Yuze Wenren, Zehan Li, Zelin Li, Zhanxu Tian, Zhengmao Zhu, Zhenhua Fan, Zhenzhen Wu, Zhichao Xu, Zhihang Yu, Zhiheng Lyu, Zhuo Jiang, Zibo Gao, Zijia Wu, Zijian Song, Zijun Sun

机构 * MiniMax 纠错

Comments A technical report from MiniMax. The authors are listed in alphabetical order. We open-source our MiniMax-M1 at https://github.com/MiniMax-AI/MiniMax-M1