InCoder-32B: Code Foundation Model for Industrial Scenarios
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918420198457344 |
|---|---|
| author | Yang, Jian Zhang, Wei Wu, Jiajun Cheng, Junhang Guo, Shawn Wang, Haowen Gu, Weicheng Du, Yaxin Li, Joseph Xu, Fanglin Li, Yizhi Jing, Lin Wang, Yuanbo Gao, Yuhan Gong, Ruihao Hao, Chuan Tao, Ran Liu, Aishan Zheng, Tuney Cui, Ganqu Li, Zhoujun Tang, Mingjie Lin, Chenghua Zhao, Wayne Xin Liu, Xianglong Zhou, Ming Dai, Bryan Lv, Weifeng |
| author_facet | Yang, Jian Zhang, Wei Wu, Jiajun Cheng, Junhang Guo, Shawn Wang, Haowen Gu, Weicheng Du, Yaxin Li, Joseph Xu, Fanglin Li, Yizhi Jing, Lin Wang, Yuanbo Gao, Yuhan Gong, Ruihao Hao, Chuan Tao, Ran Liu, Aishan Zheng, Tuney Cui, Ganqu Li, Zhoujun Tang, Mingjie Lin, Chenghua Zhao, Wayne Xin Liu, Xianglong Zhou, Ming Dai, Bryan Lv, Weifeng |
| contents | Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios that require reasoning about hardware semantics, specialized language constructs, and strict resource constraints. To address these challenges, we introduce InCoder-32B (Industrial-Coder-32B), the first 32B-parameter code foundation model unifying code intelligence across chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling. By adopting an efficient architecture, we train InCoder-32B from scratch with general code pre-training, curated industrial code annealing, mid-training that progressively extends context from 8K to 128K tokens with synthetic industrial reasoning data, and post-training with execution-grounded verification. We conduct extensive evaluation on 14 mainstream general code benchmarks and 9 industrial benchmarks spanning 4 specialized domains. Results show InCoder-32B achieves highly competitive performance on general tasks while establishing strong open-source baselines across industrial domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16790 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InCoder-32B: Code Foundation Model for Industrial Scenarios Yang, Jian Zhang, Wei Wu, Jiajun Cheng, Junhang Guo, Shawn Wang, Haowen Gu, Weicheng Du, Yaxin Li, Joseph Xu, Fanglin Li, Yizhi Jing, Lin Wang, Yuanbo Gao, Yuhan Gong, Ruihao Hao, Chuan Tao, Ran Liu, Aishan Zheng, Tuney Cui, Ganqu Li, Zhoujun Tang, Mingjie Lin, Chenghua Zhao, Wayne Xin Liu, Xianglong Zhou, Ming Dai, Bryan Lv, Weifeng Software Engineering Artificial Intelligence Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios that require reasoning about hardware semantics, specialized language constructs, and strict resource constraints. To address these challenges, we introduce InCoder-32B (Industrial-Coder-32B), the first 32B-parameter code foundation model unifying code intelligence across chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling. By adopting an efficient architecture, we train InCoder-32B from scratch with general code pre-training, curated industrial code annealing, mid-training that progressively extends context from 8K to 128K tokens with synthetic industrial reasoning data, and post-training with execution-grounded verification. We conduct extensive evaluation on 14 mainstream general code benchmarks and 9 industrial benchmarks spanning 4 specialized domains. Results show InCoder-32B achieves highly competitive performance on general tasks while establishing strong open-source baselines across industrial domains. |
| title | InCoder-32B: Code Foundation Model for Industrial Scenarios |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2603.16790 |