paper-with-me

홈 › Papers

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

2025-05-21 · Ao Liu, Botong Zhou, Can Xu, Chayse Zhou, Chenchen Zhang, Chengcheng Xu, Chenhao Wang, Decheng Wu, Dengpeng Wu, Dian Jiao, Dong Du, Dong Wang, Feng Zhang, Fengzong Lian, Guanghui Xu, Guanwei Zhang, Hai Wang, Haipeng Luo, Han Hu, Huilin Xu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jiaqi Zhu, Jinbao Xue, Jun Xia, Junqiang Zheng, Kai Liu, Kai Zhang, Kai Zheng, Kejiao Li, Keyao Wang, Lan Jiang, Lixin Liu, Lulu Wu, Mengyuan Huang, Peijie Yu, Peiqi Wang, Qian Wang, Qianbiao Xiang, Qibin Liu, Qingfeng Sun, Richard Guo, Ruobing Xie, Saiyong Yang, Shaohua Chen, Shihui Hu, Shuai Li, Shuaipeng Li, Shuang Chen, Suncong Zheng, Tao Yang, Tian Zhang, TingHao Yu, Weidong Han, Weijie Liu, Weijin Zhou, Weikang Wang, Wesleye Chen, Xiao Feng, Xiaoqin Ren, Xingwu Sun, Xiong Kuang, Xuemeng Huang, Xun Cao, Yanfeng Chen, Yang Du, Yang Zhen, Yaping Deng, Yi Shen, Yigeng Hong, Yiqi Chen, Yiqing Huang, Yuchi Deng, Yue Mao, Yulong Wang, Yuyuan Zeng, Zenan Xu, Zhanhui Kang, Zhenxiang Yan, Zheng Fang, Zhichao Hu, Zhongzhi Chen, Zhuoyu Li, Zongwei Li, Alex Yan, Ande Liang, Baitong Liu, Beiping Pan, Bin Xing, Binghong Wu, Bingxin Qu, Bolin Ni, Boyu Wu, Chen Li, Cheng Jiang, Cheng Zhang, Chengjun Liu, Chengxu Yang, Chiyu Wang, Chong Zha, Daisy Yi, Di Wang, Fanyang Lu, Fei Chen, Feifei Liu, Feng Zheng, Guanghua Yu, Guiyang Li, Guohua Wang, Haisheng Lin, Han Liu, Han Wang, Hao Fei, Hao Lu, Haoqing Jiang, Haoran Sun, Haotian Zhu, Huangjin Dai, Huankui Chen, Huawen Feng, Huihui Cai, Huxin Peng, Jackson Lv, Jiacheng Shi, Jiahao Bu, Jianbo Li, Jianglu Hu, Jiangtao Guan, Jianing Xu, Jianwei Cai, Jiarong Zhang, Jiawei Song, Jie Jiang, Jie Liu, Jieneng Yang, Jihong Zhang, Jin lv, Jing Zhao, Jinjian Li, JinXing Liu, Jun Zhao, Juntao Guo, Kai Wang, Kan Wu, Lei Fu, Lei He, Lei Wang, Li Liu, Liang Dong, Liya Zhan, Long Cheng, Long Xu, Mao Zheng, Meng Liu, Mengkang Hu, Nanli Chen, Peirui Chen, Peng He, Pengju Pan, Pengzhi Wei, Qi Yang, Qi Yi, Roberts Wang, Rongpeng Chen, Rui Sun, Rui Yang, Ruibin Chen, Ruixu Zhou, Shaofeng Zhang, Sheng Zhang, Shihao Xu, Shuaishuai Chang, Shulin Liu, Siqi Wang, Songjia Feng, Songling Yuan, Tao Zhang, Tianjiao Lang, Tongkai Li, Wei Deng, Wei Li, Weichao Wang, Weigang Zhang, Weixuan Sun, Wen Ouyang, Wenxiang Jiao, Wenzhi Sun, Wenzhuo Jia, Xiang Zhang, Xiangyu He, Xianshun Ren, Xiaoying Zhu, Xiaolong Guo, Xiaoxue Li, Xiaoyu Ma, Xican Lu, Xinhua Feng, Xinting Huang, Xinyu Guan, Xirui Li, Xu Zhang, Xudong Gao, Xun Luo, Xuxiang Qi, Yangkun Chen, Yangyu Tao, Yanling Xiao, Yantao Mai, Yanze Chen, Yao Ding, Yeting Yang, YiFan Song, Yifan Yang, Yijiao Zhu, Yinhe Wu, Yixian Liu, Yong Yang, Yuanjun Cai, Yuanlin Tu, Yue Zhang, Yufei Huang, YuHang Zhou, Yuhao Jiang, Yuhong Liu, Yuhui Hu, YuJin Lin, Yun Yang, Yunhao Wang, Yusong Zhang, Zekun Wu, Zelong Zhang, Zhan Yu, Zhaoliang Yang, Zhe Zhao, Zheng Li, Zhenyu Huang, Zhiguang Liu, Zhiqing Kui, Zhiyin Zeng, Zhiyuan Xiong, Zhuo Han, Zifan Wu, Zigang Geng, Zilong Zhao, Ziyan Tang, Ziyuan Zhu, Zonglei Zhu, Zhijiang Xu

As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid responses for simple queries and deep "thinking" modes for complex problems, optimizing computational resources. Architecturally, this 56B activated (560B total) parameter model employs 128 layers (Mamba2, Attention, FFN) with an innovative AMF/MF block pattern. Faster Mamba2 ensures linear complexity, Grouped-Query Attention minimizes KV cache, and FFNs use an MoE structure. Pre-trained on 16T high-quality tokens, it supports a 256K context length and is the first industry-deployed large-scale Mamba model. Our comprehensive post-training strategy enhances capabilities via Supervised Fine-Tuning (3M instructions), a novel Adaptive Long-short CoT Fusion method, Multi-round Deliberation Learning for iterative improvement, and a two-stage Large-scale Reinforcement Learning process targeting STEM and general instruction-following. Evaluations show strong performance: overall top 7 rank on LMSYS Chatbot Arena with a score of 1356, outperforming leading models like Gemini-2.0-Flash-001 (1352) and o4-mini-2025-04-16 (1345). TurboS also achieves an average of 77.9% across 23 automated benchmarks. Hunyuan-TurboS balances high performance and efficiency, offering substantial capabilities at lower inference costs than many reasoning models, establishing a new paradigm for efficient large-scale pre-trained models.

📄 PDF Abstract BibTeX arXiv:2505.15431

Code (0)

등록된 구현이 없습니다.

Tasks

ChatbotInstruction FollowingMambaMixture-of-Experts

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
MoE 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Grouped-query attention 설명 없음
Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients

2024-01-22 · Mengdi Wang, Anna Bodonhelyi, Efe Bozkir, Enkelejda Kasneci

Federated learning is a distributed collaborative machine learning paradigm that has gained strong momentum in recent years. In federated learning, a central server periodically coordinates models with clients and aggreg…

Federated Learning

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

2024-05-14 · Zhimin Li, Jianwei Zhang, Qin Lin, Jiangfeng Xiong 외

We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positi…

Image GenerationLanguage ModelingLanguage ModellingLarge Language Model+2

Lisbon: Evaluating TurboSemanticParser on Multiple Languages and Out-of-Domain Data

2015-06-01 · SEMEVAL 2015 6 · Mariana S. C. Almeida, Andr{\'e} F. T. Martins
Dependency ParsingDomain AdaptationStructured Prediction

Hunyuan-A13B Technical Report

2026-09-23 · Tencent Hunyuan Team, Ao Liu, Botong Zhou, Can Xu 외 hf

We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability,…

Computational EfficiencyReinforcement Learning

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

2025-05-07 · Teng Hu, Zhentao Yu, Zhengguang Zhou, Sen Liang 외

Customized video generation aims to produce videos featuring specific subjects under flexible user-defined conditions, yet existing methods often struggle with identity consistency and limited input modalities. In this p…

Human-Domain Subject-to-VideoSingle-Domain Subject-to-VideoVideo AlignmentVideo Generation