Publications

StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion

Yutong Wu, Di Huang, Ruosi Wan, Yue Peng, Shijie Shang, Chenrui Cao, Lei Qi, Rui Zhang, Zidong Du, Jie Yan, Xing Hu

AAAI 2026 Oral

AGON: Automated Design Framework for Customizing Processors from ISA Documents

Chongxiao Li, Di Huang, Pengwei Jin, Tianyun Ma, Husheng Han, Shuyao Cheng, Yifan Hao, Yongwei Zhao, Guanglin Xu, Zidong Du, Rui Zhang, Xiaqing Li, Yuanbo Wen, Xing Hu, Qi Guo

IEEE TCAD 2025

Mosaic: Exploiting Instruction-Level Parallelism on Deep Learning Accelerators with iTex Tessellation

Jianxing Xu, Yuanbo Wen, Zikang Liu, Ruibai Xu, Tingfeng Ruan, Jun Bi, Rui Zhang, Di Huang, Xinkai Song, Yifan Hao, others

Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct

Yutong Wu, Di Huang, Wenxuan Shi, Wei Wang, Yewen Pu, Lingzhe Gao, Shihao Liu, Ziyuan Nan, Kaizhao Yuan, Rui Zhang, others

Proceedings of the AAAI Conference on Artificial Intelligence

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions

Pucheng Dang, Di Huang, Dong Li, Kang Chen, Yuanbo Wen, Qi Guo, Xing Hu

NeurIPS 2025 Spotlight

QiMeng-Xpiler: Transcompiling tensor programs for deep learning systems with a neural-symbolic approach

Shouyang Dong, Yuanbo Wen, Jun Bi, Di Huang, Jiaming Guo, Jianxing Xu, Ruibai Xu, Xinkai Song, Yifan Hao, Xuehai Zhou, others

arXiv preprint arXiv:2505.02146

QiMeng: Fully Automated Hardware and Software Design for Processor Chip

Rui Zhang, Yuanbo Wen, Shuyao Cheng, Di Huang, Shaohui Peng, Jiaming Guo, Pengwei Jin, Jiacheng Zhao, Tianrui Ma, Yaoyu Zhu, others

arXiv preprint arXiv:2506.05007

Cambricon-SR: An Accelerator for Neural Scene Representation with Sparse Encoding Table

Tianbo Liu, Xinkai Song, Zhifei Yue, Rui Wen, Xing Hu, Zhuoran Song, Yuanbo Wen, Yifan Hao, Wei Li, Zidong Du, others

Proceedings of the 52nd Annual International Symposium on Computer Architecture

CodeV: Empowering llms with hdl generation through multi-level summarization

CodeV: Empowering llms with hdl generation through multi-level summarization

Yang Zhao, Di Huang, Chongxiao Li, Pengwei Jin, Muxin Song, Yinan Xu, Ziyuan Nan, Mingju Gao, Tianyun Ma, Lei Qi, Yansong Pan, Zhenxing Zhang, Rui Zhang, Xishan Zhang, Zidong Du, Xing Hu

IEEE TCAD 2025

The first model of the CodeV series, supporting Verilog and Chisel generation and fill-in-middle. Can be applied to VSCode and VIM as a code completion plugin.

Project PagePaperCodeDataModel

Realbench: Benchmarking verilog generation models with real-world ip designs

Pengwei Jin, Di Huang, Chongxiao Li, Shuyao Cheng, Yang Zhao, Xinyao Zheng, Jiaguo Zhu, Shuyi Xing, Bohan Dou, Rui Zhang, Zidong Du, Xing Hu

Preprint

Swift: High Parallelism Program Generation of Tensor Operators for Accelerating Deep Learning Inference

Xiyue Yu, Jun Bi, Yuanbo Wen, Jianxing Xu, Di Huang, Jiaming Guo, Wei Li, Zidong Du, Jing Li, Tianshi Chen, others

ACM Transactions on Architecture and Code Optimization

QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation

Yang Zhang, Rui Zhang, Jiaming Guo, Lei Huang, Di Huang, Yunpu Zhao, Shuyao Cheng, Pengwei Jin, Chongxiao Li, Zidong Du, others

arXiv preprint arXiv:2510.19296

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

Yaoyu Zhu, Di Huang, Hanqi Lyu, Xiaoyun Zhang, Chongxiao Li, Wenxuan Shi, Yutong Wu, Jianan Mu, Jinghua Wang, Pengwei Jin, Shuyao Cheng, Shengwen Liang, Xishan Zhang, Rui Zhang, Zidong Du, Qi Guo, Xing Hu, Yunji Chen

NeurIPS 2025

Model specialized in Verilog generation to incorporate reasoning capabilities, showing test-time scaling.

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

Hainan Fang, Yuanbo Wen, Jun Bi, Yihan Wang, Tonghui He, Yanlin Tang, Di Huang, Jiaming Guo, Rui Zhang, Qi Guo, others

arXiv preprint arXiv:2511.01183

QiMeng-CRUX: Narrowing the Gap between Natural Language and Verilog via Core Refined Understanding eXpression

Lei Huang, Rui Zhang, Jiaming Guo, Yang Zhang, Di Huang, Shuyao Cheng, Pengwei Jin, Chongxiao Li, Zidong Du, Xing Hu, others

arXiv preprint arXiv:2511.20099

A Constructive Proof of the Generalized Riemann Hypothesis for Function Fields over Finite Constants

A Constructive Proof of the Generalized Riemann Hypothesis for Function Fields over Finite Constants

John Smith, Jiale Liu†, Alan Turing

Proceedings of the 2024 International Congress of Mathematicians (ICM)

A constructive proof demonstrating the validity of the Generalized Riemann Hypothesis for function fields using spectral interpretation of the Frobenius automorphism.

Paper

Hypothesis, verification, and induction: grounding large language models with self-driven skill learning

Shaohui Peng, Xing Hu, Qi Yi, Rui Zhang, Jiaming Guo, Di Huang, Zikang Tian, Ruizhi Chen, Zidong Du, Qi Guo, others

Proceedings of the AAAI Conference on Artificial Intelligence

Harmonia: A Unified Architecture for Efficient Deep Symbolic Regression

Tianyun Ma, Yuanbo Wen, Xinkai Song, Pengwei Jin, Di Huang, Husheng Han, Ziyuan Nan, Zhongkai Yu, Shaohui Peng, Yongwei Zhao, others

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

Cambricon-llm: A chiplet-based hybrid architecture for on-device inference of 70b llm

Zhongkai Yu, Shengwen Liang, Tianyun Ma, Yunke Cai, Ziyuan Nan, Di Huang, Xinkai Song, Yifan Hao, Jie Zhang, Tian Zhi, others

2024 57th IEEE/ACM International Symposium on Microarchitecture (MICRO)

Emergent communication for numerical concepts generalization

Enshuai Zhou, Yifan Hao, Rui Zhang, Yuxuan Guo, Zidong Du, Xishan Zhang, Xinkai Song, Chao Wang, Xuehai Zhou, Jiaming Guo, others

Proceedings of the AAAI Conference on Artificial Intelligence

Flew over learning trap: Learn unlearnable samples by progressive staged training

Pucheng Dang, Xing Hu, Kaidi Xu, Jinhao Duan, Di Huang, Husheng Han, Rui Zhang, Zidong Du, Qi Guo, Yunji Chen

arXiv preprint arXiv:2306.02064

Online symbolic regression with informative query

Pengwei Jin, Di Huang, Rui Zhang, Xing Hu, Ziyuan Nan, Zidong Du, Qi Guo, Yunji Chen

Proceedings of the AAAI Conference on Artificial Intelligence

ANPL: towards natural programming with interactive decomposition

Di Huang, Ziyuan Nan, Xing Hu, Pengwei Jin, Shaohui Peng, Yuanbo Wen, Rui Zhang, Zidong Du, Qi Guo, Yewen Pu, Yunji Chen

NeurIPS 2023

Emergent communication for rules reasoning

Yuxuan Guo, Yifan Hao, Rui Zhang, Enshuai Zhou, Zidong Du, Xinkai Song, Yuanbo Wen, Yongwei Zhao, Xuehai Zhou, Jiaming Guo, others

Advances in Neural Information Processing Systems

Neural Program Synthesis with Query

Di Huang, Rui Zhang, Xing Hu, Xishan Zhang, Pengwei Jin, Nan Li, Zidong Du, Qi Guo, Yunji Chen

ICLR 2022

Rethinking the importance of quantization bias, toward full low-bit training

Chang Liu, Xishan Zhang, Rui Zhang, Ling Li, Shiyi Zhou, Di Huang, Zhen Li, Zidong Du, Shaoli Liu, Tianshi Chen

IEEE Transactions on Image Processing

A decomposable winograd method for n--d convolution acceleration in video analysis

Di Huang, Rui Zhang, Xishan Zhang, Fan Wu, Xianzhuo Wang, Pengwei Jin, Shaoli Liu, Ling Li, Yunji Chen

International Journal of Computer Vision

Fixed-point back-propagation training

Xishan Zhang, Shaoli Liu, Rui Zhang, Chang Liu, Di Huang, Shiyi Zhou, Jiaming Guo, Qi Guo, Zidong Du, Tian Zhi, others

Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

DWM: A decomposable Winograd method for convolution acceleration

Di Huang, Xishan Zhang, Rui Zhang, Tian Zhi, Deyuan He, Jiaming Guo, Chang Liu, Qi Guo, Zidong Du, Shaoli Liu, others

Proceedings of the AAAI conference on artificial intelligence

Adaptive precision training: Quantify back propagation in neural networks with fixed-point numbers

Xishan Zhang, Shaoli Liu, Rui Zhang, Chang Liu, Di Huang, Shiyi Zhou, Jiaming Guo, Yu Kang, Qi Guo, Zidong Du, others

arXiv preprint arXiv:1911.00361