홈 › Papers

Hunyuan-A13B Technical Report

2026-09-23 · Tencent Hunyuan Team, 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, Jihong Zhang, 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, Zhen Yang, Yangyu Tao, Yaping Deng, Yi Shen, Yigeng Hong, Yiqi Chen 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 efficiency, and deployment cost. The model is pretrained on a rigorously filtered 20T-token corpus with enhanced STEM data curation, improving factual reliability and reasoning ability. High-quality supervised fine-tuning and large-scale reinforcement learning further enhance its overall performance. Hunyuan-A13B also introduces a dual-mode Chain-of-Thought framework that adapts reasoning depth to task complexity: fast thinking for routine queries and slow thinking for complex, multi-step problems. Evaluations show competitive performance across mathematics, science, programming, general language understanding, and agent tasks, often approaching that of much larger models. Its high inference throughput makes it suitable for latency-sensitive applications. We release Hunyuan-A13B to support open research and practical LLM deployment.

📄 PDF Abstract BibTeX arXiv:2609.27284

Code (3)

Tavish9/awesome-daily-AI-arxiv ★ 121

Valiant-Cat/hfpaper

arxivsub/arXivSub_daily_arxiv ★ 4

Tasks

Computational Efficiency Reinforcement Learning

HunyuanImage 3.0 Technical Report

2025-09-28 · Tencent Hunyuan Foundation Model Team arxiv

We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with its image generation module publicly available. The achievement of Huny…

Image Generation

Hunyuan-MT Technical Report

2025-09-05 · Mao Zheng, Zheng Li, Bingxin Qu, Mingyang Song 외 arxiv

In this report, we introduce Hunyuan-MT-7B, our first open-source multilingual translation model, which supports bidirectional translation across 33 major languages and places a special emphasis on translation between Ma…

Reinforcement Learning Machine Translation

HunyuanVideo 1.5 Technical Report

2025-11-24 · Bing Wu, Chang Zou, Changlin Li, Duojun Huang 외 arxiv

We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference…

Video Super-Resolution Video Generation

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

2025-09-16 · Biwen Lei, Yang Li, Xinhai Liu, Shuhui Yang 외 arxiv

The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered c…

3D Generation

HunyuanOCR Technical Report

2025-11-24 · Hunyuan Vision Team, Pengyuan Lyu, Xingyu Wan, Gengluo Li 외 arxiv

This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Native Vision Transformer (ViT) and a ligh…

Reinforcement Learning Text Spotting