Biography

I am a Ph.D. candidate in Computer Science at the University of Maryland, College Park, advised by Prof. Ang Li. I study efficient language and multimodal models, connecting an understanding of model representations with methods for training, adaptation, and inference.

My work asks which computations a model needs, and how to allocate them. I investigate representation geometry and structural redundancy, then use these insights to develop dynamic depth routing, Mixture-of-Experts inference, and parameter-efficient adaptation. Recent projects extend this work to unified multimodal models, video understanding, and dense retrieval.

My research experience spans Google DeepMind & Ads (efficient post-training), ByteDance Seed (multimodal models), Tencent AI Lab, and JD Explore Academy. I received the Qualcomm Innovation Fellowship (QIF) North America and the UMD CS Certificate of Outstanding Achievement.

I am seeking full-time research opportunities in foundation models, inference acceleration, and efficient AI applications. Please get in touch to discuss potential opportunities.

News

Earlier news (2022 – January 2026)

Research Experience

Google DeepMind & Ads
Student Researcher · Mountain View, CA
Efficient Post-Training
ByteDance Seed
Research Intern · San Jose, CA
Multimodal Foundation Models
Tencent AI Lab
Research Intern · Bellevue, WA
Sparse and Efficient Large Language Models
JD Explore Academy
Research Intern · Beijing, China
Efficient and Adaptive Methods for NLP

Selected Publications

Model Understanding

Shwai He, Haichao Zhang, Shen Yan, "Disentangling Representation Evolution in Transformers through Directional Decomposition", Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026). Project Paper Code 🧭 Story & Reflection
BibTeX
@inproceedings{he2026disentangling,
  title={Disentangling Representation Evolution in Transformers through Directional Decomposition},
  author={He, Shwai and Zhang, Haichao and Yan, Shen},
  booktitle={Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2026}
}
Shwai He, Guoheng Sun, Haichao Zhang, Yun Fu, Ang Li, "Demystifying When Pruning Works via Representation Hierarchies", Proceedings of the Forty-third International Conference on Machine Learning (ICML 2026). Project Paper Code 🌱 Story & Reflection
BibTeX
@inproceedings{he2026demystifying,
  title={Demystifying When Pruning Works via Representation Hierarchies},
  author={He, Shwai and Sun, Guoheng and Zhang, Haichao and Fu, Yun and Li, Ang},
  booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  year={2026}
}
Shwai He*, Guoheng Sun*, Zheyu Shen, Ang Li, "Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping", Transactions on Machine Learning Research (TMLR). Project Paper Code Model 🌬️ Story & Reflection
BibTeX
@article{he2026uncovering,
  title={Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping},
  author={He, Shwai and Sun, Guoheng and Shen, Zheyu and Li, Ang},
  journal={Transactions on Machine Learning Research (TMLR)},
  year={2026}
}

Inference Acceleration

Shwai He, Weilin Cai, Jiayi Huang, Ang Li, "Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts", Proceedings of the Fourteenth International Conference on Learning Representations (ICLR 2026). Project Paper Code 🎒 Story & Reflection
BibTeX
@inproceedings{he2026capacity,
  title={Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts},
  author={He, Shwai and Cai, Weilin and Huang, Jiayi and Li, Ang},
  booktitle={Proceedings of the 14th International Conference on Learning Representations (ICLR)},
  year={2026}
}
Weilin Cai, Le Qin, Shwai He, Junwei Cui, Ang Li, Jiayi Huang, "DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction", Proceedings of the Forty-third International Conference on Machine Learning (ICML 2026). Paper
BibTeX
@inproceedings{cai2026dualsparse,
  title={DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction},
  author={Cai, Weilin and Qin, Le and He, Shwai and Cui, Junwei and Li, Ang and Huang, Jiayi},
  booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  year={2026}
}
Shwai He, Tao Ge, Guoheng Sun, Bowei Tian, Xiaoyang Wang, Dong Yu, "Router-Tuning: A Simple and Effective Approach for Dynamic Depth", Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). Project Paper Code 🔍 Story & Reflection
BibTeX
@inproceedings{he2025router,
  title={Router-Tuning: A Simple and Effective Approach for Dynamic Depth},
  author={He, Shwai and Ge, Tao and Sun, Guoheng and Tian, Bowei and Wang, Xiaoyang and Yu, Dong},
  booktitle={Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2025}
}
Shwai He*, Daize Dong*, Liang Ding, Ang Li, "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques", Transactions on Machine Learning Research (TMLR). Paper Code 🧪 Story & Reflection
BibTeX
@article{he2025towards,
  title={Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques},
  author={He, Shwai and Dong, Daize and Ding, Liang and Li, Ang},
  journal={Transactions on Machine Learning Research (TMLR)},
  year={2025}
}
Shwai He, Run-Ze Fan, Liang Ding, Li Shen, Tianyi Zhou, Dacheng Tao, "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts", Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 Oral). Paper Code 💡 Story & Reflection
BibTeX
@inproceedings{he2023merging,
  title={Merging Experts into One: Improving Computational Efficiency of Mixture of Experts},
  author={He, Shwai and Fan, Run-Ze and Ding, Liang and Shen, Li and Zhou, Tianyi and Tao, Dacheng},
  booktitle={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2023}
}
Shwai He, Liang Ding, Daize Dong, Boan Liu, Fuqiang Yu, Dacheng Tao, "PAD-Net: An Efficient Framework for Dynamic Networks", Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). Paper Code 🌳 Story & Reflection
BibTeX
@inproceedings{he2023pad,
  title={PAD-Net: An Efficient Framework for Dynamic Networks},
  author={He, Shwai and Ding, Liang and Dong, Daize and Liu, Boan and Yu, Fuqiang and Tao, Dacheng},
  booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)},
  year={2023}
}
Shwai He, Chenbo Jiang, Daize Dong, Liang Ding, "SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution", IEEE/CVF Winter Conference on Applications of Computer Vision, 2023 (WACV 2023). Paper 📷 Story & Reflection
BibTeX
@inproceedings{he2023sdconv,
  title={SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution},
  author={He, Shwai and Jiang, Chenbo and Dong, Daize and Ding, Liang},
  booktitle={IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year={2023}
}

Efficient Adaptation

Yibin Lei*, Shwai He*, Ang Li, Andrew Yates, "Making Large Language Models Efficient Dense Retrievers", Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026). Paper Code Models 🌊 Story & Reflection
BibTeX
@inproceedings{lei2026making,
  title={Making Large Language Models Efficient Dense Retrievers},
  author={Lei, Yibin and He, Shwai and Li, Ang and Yates, Andrew},
  booktitle={Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL)},
  year={2026}
}
Shwai He, Liang Ding, Daize Dong, Miao Zhang, Dacheng Tao, "SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters", Findings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022). Paper Code 🏛️ Story & Reflection
BibTeX
@inproceedings{he2022sparseadapter,
  title={SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters},
  author={He, Shwai and Ding, Liang and Dong, Daize and Zhang, Miao and Tao, Dacheng},
  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2022},
  year={2022}
}

Multimodal Learning & Vision

Shwai He, Chaorui Deng, Ang Li, Shen Yan, "Understanding and Harnessing Sparsity for Unified Multimodal Models", Transactions on Machine Learning Research (TMLR). Project Paper Code 🎼 Story & Reflection
BibTeX
@article{he2026understanding,
  title={Understanding and Harnessing Sparsity for Unified Multimodal Models},
  author={He, Shwai and Deng, Chaorui and Li, Ang and Yan, Shen},
  journal={Transactions on Machine Learning Research (TMLR)},
  year={2026}
}
Haichao Zhang, Wenhao Chai, Shwai He, Ang Li, Yun Fu, "Dense Video Understanding with Inter-tokenization Acceleration", European Conference on Computer Vision (ECCV 2026).
BibTeX
@inproceedings{zhang2026dense,
  title={Dense Video Understanding with Inter-tokenization Acceleration},
  author={Zhang, Haichao and Chai, Wenhao and He, Shwai and Li, Ang and Fu, Yun},
  booktitle={European Conference on Computer Vision (ECCV)},
  year={2026}
}

AI Applications

Hongtai Jing, Zhengtao Gao, Sheng Xu, Tao Shen, Zhangzhi Peng, Shwai He, Tao You, Shuang Ye, Wei Lin, Siqi Sun, "Accurate prediction of antibody function and structure using bio-inspired antibody language model", Briefings in Bioinformatics, 25(4), bbae245, 2024. Paper
BibTeX
@article{jing2024accurate,
  title={Accurate prediction of antibody function and structure using bio-inspired antibody language model},
  author={Jing, Hongtai and Gao, Zhengtao and Xu, Sheng and Shen, Tao and Peng, Zhangzhi and He, Shwai and You, Tao and Ye, Shuang and Lin, Wei and Sun, Siqi},
  journal={Briefings in Bioinformatics},
  volume={25},
  number={4},
  pages={bbae245},
  year={2024},
  doi={10.1093/bib/bbae245}
}
Shwai He, Shi Gu, "Multi-modal Attention Network for Stock Movements Prediction", the AAAI-22 Workshop on Knowledge Discovery from Unstructured Data in Financial Service (KDF 2022). Paper
BibTeX
@article{he2022multimodal,
  title={Multi-modal Attention Network for Stock Movements Prediction},
  author={He, Shwai and Gu, Shi},
  journal={AAAI-22 Workshop on Knowledge Discovery from Unstructured Data in Financial Service},
  year={2022}
}

Industry Model Reports

ByteDance Seed, "Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity", Technical Report, 2026. Report
BibTeX
@misc{seed2026seed20,
  title={Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity},
  author={{ByteDance Seed}},
  year={2026},
  eprint={2607.00248},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2607.00248}
}
Changtong Zan, Keqin Peng, Liang Ding, Baopu Qiu, Boan Liu, Shwai He, Qingyu Lu, Zheng Zhang, Chuang Liu, Weifeng Liu, Yibing Zhan, Dacheng Tao, "Vega-MT: The JD Explore Academy Translation System for WMT", The Conference on Machine Translation, 2022 (WMT 2022). Paper
BibTeX
@inproceedings{zan2022vega,
  title={Vega-MT: The JD Explore Academy Translation System for WMT},
  author={Zan, Changtong and Peng, Keqin and Ding, Liang and Qiu, Baopu and Liu, Boan and He, Shwai and Lu, Qingyu and Zhang, Zheng and Liu, Chuang and Liu, Weifeng and Zhan, Yibing and Tao, Dacheng},
  booktitle={Proceedings of the Seventh Conference on Machine Translation (WMT)},
  year={2022}
}

Teaching

  • Spring 2025: Teaching Assistant for CMSC 320 (Introduction to Data Science)
  • Fall 2024: Teaching Assistant for CMSC 250 (Discrete Structures)
  • Spring 2024: Teaching Assistant for CMSC 351 (Algorithms)

Last updated: September 21, 2026