Weiping Yan

I am Weiping Yan (闫维平), an undergraduate researcher working at the intersection of machine learning, scientific inquiry, and engineering design. I have pursued concurrent undergraduate studies across Computer Science & Engineering, Electrical Engineering, and Applied Physics at Delft University of Technology and Eindhoven University of Technology. During that period, I participated in the TU/e Honors Academy — Honors Bachelor Program and the TU Delft Honours Programme Bachelor (HPB) in 2025–2026 before transferring. I am now an Electrical Engineering and Computer Science student in the University of Minnesota College of Science and Engineering; my studies began when Fall 2026 classes started on September 8, 2026.

My current interests are artificial intelligence, natural language processing, microelectronics, and electronic design automation. I value careful problem formulation, reproducible evidence, and clear boundaries between completed work and research in progress.

My research and teaching experience includes an NLP Research Internship with the Minnesota NLP Group since July 2026, as well as work at The Chinese University of Hong Kong, Eindhoven University of Technology, and Zhangjiang Laboratory. The Minnesota NLP role is a research position and is separate from my undergraduate studies. Earlier independent work on PM2.5 and respiratory-disease incidence used synthetic, randomly generated data for an exploratory Python analysis and led to a published article in Theoretical and Natural Science. It was an independent student project, not an appointment at Carnegie Mellon University, and it should not be read as an analysis of clinical or population exposure records.

Contact

The best way to reach me is at yan00944@umn.edu. I also receive mail at vipinapple986@gmail.com. Links to my research and professional profiles appear below.

news

Sep 08, 2026	I began my undergraduate studies in Electrical Engineering and Computer Science at the College of Science and Engineering at the University of Minnesota as Fall 2026 classes began on September 8, 2026.
Sep 08, 2026	A revised version of our co-authored manuscript, “OAM-GA: Reliability-Guided Motion Completion for Occlusion-RobustGaussian Avatars,” was posted on OpenReview for DAI 2026. The submission remains under review, with a decision pending; it has not been accepted or published.
Sep 08, 2026	Six of my pull requests were merged upstream between August 4 and September 8, 2026: Power Grid Model #1516, #1518, and #1540; LensKit #1209; M* #235; and PISA #641. The accepted changes cover update validation and sensor semantics, performance documentation, recommender warnings, media decoding and error handling, and retrieval type safety.
Jul 01, 2026	I began an NLP Research Internship with the Minnesota NLP Group at the University of Minnesota.
May 02, 2026	I co-founded Veylora Labs to explore executive-intelligence systems for organizational decision support.

selected publications

Submitted
OAM-GA: Reliability-Guided Motion Completion for Occlusion-RobustGaussian Avatars

Xiang Wang, Xu Yan, Letian Pei, and Weiping Yan

2026

Submitted to DAI 2026; under review, decision pending, and not yet accepted or published.

Abs Bib HTML

Reconstructing sharp and animatable 3D human avatars from motion-blurred videos remains challenging under partial occlusion, where unreliable SMPL estimates can propagate pose errors into Gaussian deformation. To address this problem, we propose OAM-GA, an occlusion-robust framework for motion-aware Gaussian avatar reconstruction. OAM-GA estimates joint-wise reliability and restores missing motion using visible temporal context. Specifically, a Bidirectional Wavelet Masked Motion Completion module decomposes motion features into low- and high-frequency components and reconstructs contiguous occluded intervals from observations before and after the masked region. Clean–occluded contrastive consistency learning further encourages occlusion-invariant motion representations, while reliability-guided residual refinement selectively corrects uncertain joints and preserves reliable ones. Experiments on BlurZJU and BS-Human show that OAM-GA improves overall reconstruction robustness and perceptual quality under diverse occlusion patterns while maintaining the rendering fidelity of the original baseline.
@unpublished{wang2026oamga, title = {{OAM-GA}: Reliability-Guided Motion Completion for Occlusion-RobustGaussian Avatars}, author = {Wang, Xiang and Yan, Xu and Pei, Letian and Yan, Weiping}, year = {2026}, note = {Submitted to {DAI} 2026; under review, decision pending, and not yet accepted or published.}, url = {https://openreview.net/forum?id=UV2UJ4VHf7}, }

TNS

Effect of PM2.5 air pollution on the incidence of respiratory diseases: A Python-based data analysis

Weiping Yan

Theoretical and Natural Science, Nov 2023

DOI Bib HTML PDF

@article{yan2023pm25,
  title = {Effect of {PM2.5} air pollution on the incidence of respiratory diseases: A {Python}-based data analysis},
  author = {Yan, Weiping},
  journal = {Theoretical and Natural Science},
  volume = {8},
  number = {1},
  pages = {70--75},
  year = {2023},
  month = nov,
  publisher = {EWA Publishing},
  doi = {10.54254/2753-8818/8/20240361},
  url = {https://tns.ewapub.com/article/view/6279},
}