DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Hengqing Zhang, Feiyu Xia, Dongjie Ji, D C Li, Haowen Luo(Hangzhou Wanxiang Polytechnic), Chenze Shao, Daya Guo(Sun Yat-sen University), Guangbo Hao(University College Cork), Chengyu Hou, Anyi Xu, Chengda Lu(China University of Geosciences), Haotian Yuan, Deli Chen(Hainan Medical University), Hanwei Xu, Luo Haoming, Bingzheng Xu, Fangyun Lin, Guowei Li(Institute of Computing Technology), Erhang Li, Haoling Zhang, Guanting Chen, D Yang, Bingxuan Wang, Fangzhou Yuan, Guolai Meng, Bochao Wu, Chenggang Zhao, Bing Xue, Haoran Wei, Chengqi Deng, Fang Wei, Haofen Liang, Bangcai Lin, Haowei Zhang, Chong Ruan, Chaofan Lin, Haoyu Chen, Chenchen Ling, Chen Dong, Fucong Dai, Bowei Zhang, Conner Sun, Hao Li, Han Zhang, Han Yu, Chenhao Xu, Damai Dai(Microsoft Research (India)), Guoai Cao, Haozhe Ji
arXiv (Cornell University)
April 26, 2026
Cited by 0
Related Papers
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
|Unknown|2020|2.5k
UniXcoder: Unified Cross-Modal Pre-training for Code Representation
|Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)|2022|554
Can Open Large Language Models Catch Vulnerabilities?
|arXiv (Cornell University)|2025|501
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
|arXiv (Cornell University)|2021|415