Yuchen Shen

I am a first-year PhD student at the Machine Learning Department, Carnegie Mellon University. I am advised by Professor Aran Nayebi, and I am interested in building capable, autonomous AI systems, with applications such as AI scientists, trading bots, personal assistants, etc. Guided by this goal, I am particularly interested in:

safety: how do we build capable and safe AI systems? (e.g., a trading bot should know all the trading strategies, meanwhile avoiding illegal actions)
creativity: how can the AI systems discover new patterns and strategies? (e.g., an AI scientist should be able to propose novel solutions for new scientific challenges)
memory: how can we effectively augment AI systems to digest more information? (e.g., a personal assistant should be able to backtrack different daily conversations with the user)

During my master’s, I was fortunate to work with Professor Aran Nayebi on brain-inspired ML, with Professor Barnabás Póczos on generative models for molecules, and with Professor Leman Akoglu on zero-shot outlier detection. Additionally, I was interested in optimization and had the privilege of working with Professor Xiaorui Liu on decentralized algorithms.

During my undergraduate years, I concentrated on Natural Language Processing (NLP) and worked on summarization, few-shot sentiment analysis, and chatbots.

Email is the best way to reach me and please feel free to send me an email to discuss research! I try to read all my emails carefully, but don’t hesitate to send another one if you don’t receive my reply after one week!

news

Sep 28, 2025	One paper (FoMo-0D) accepted by TMLR
Sep 19, 2025	One paper (Tactile Whisking) accepted by NeurIPS 2025 as oral
Jan 23, 2025	One paper (ChemGuide) accepted by ICLR 2025
Sep 26, 2024	One paper (ProTransformer) accepted by NeurIPS 2024
Jun 17, 2024	Two papers (GraphBPE, Non-differentiable Guidance) accepted by ICML 2024 AI for Science Workshop

selected publications

EMNLP

Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category Detection

Fei Zhao* , Yuchen Shen* , Zhen Wu , and Xinyu Dai

In Findings of the Association for Computational Linguistics: EMNLP 2022 , 2022

Bib PDF

@inproceedings{zhao-etal-2022-label,
  title = {Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category Detection},
  author = {Zhao*, Fei and Shen*, Yuchen and Wu, Zhen and Dai, Xinyu},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2022},
  year = {2022},
  address = {Abu Dhabi, United Arab Emirates},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2022.findings-emnlp.177},
  doi = {10.18653/v1/2022.findings-emnlp.177},
  pages = {2390--2402},
}

TMLR

FoMo-0D: A Foundation Model for Zero-shot Tabular Outlier Detection

Yuchen Shen , Haomin Wen , and Leman Akoglu

Transactions on Machine Learning Research, 2025

Bib PDF

@article{shen2025fomod,
  title = {FoMo-0D: A Foundation Model for Zero-shot Tabular Outlier Detection},
  author = {Shen, Yuchen and Wen, Haomin and Akoglu, Leman},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2025},
  url = {https://openreview.net/forum?id=XCQzwpR9jE},
}

NeurIPS

Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain

Trinity Chung* , Yuchen Shen* , Nathan C. L. Kong , and Aran Nayebi

2025

Bib PDF

@misc{chung2025taskoptimizedconvolutionalrecurrentnetworks,
  title = {Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain},
  author = {Chung*, Trinity and Shen*, Yuchen and Kong, Nathan C. L. and Nayebi, Aran},
  year = {2025},
  eprint = {2505.18361},
  archiveprefix = {arXiv},
  primaryclass = {q-bio.NC},
  url = {https://arxiv.org/abs/2505.18361},
}

ICLR

Chemistry-Inspired Diffusion with Non-Differentiable Guidance

Yuchen Shen* , Chenhao Zhang* , Sijie Fu* , Chenghui Zhou , Newell Washburn , and 1 more author

In The Thirteenth International Conference on Learning Representations , 2025

Bib PDF

@inproceedings{shen2025chemistryinspired,
  title = {Chemistry-Inspired Diffusion with Non-Differentiable Guidance},
  author = {Shen*, Yuchen and Zhang*, Chenhao and Fu*, Sijie and Zhou, Chenghui and Washburn, Newell and Poczos, Barnabas},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  year = {2025},
  url = {https://openreview.net/forum?id=4dAgG8ma3B},
}