Under Review ✍️

  1. Ye, Z., Yan, Z., He, J., Kasriel, T., Yang, K., & Song, D. VERINA: Benchmarking Verifiable Code Generation. Under review at ICLR 2026.

    • arXiv: 2505.23135
    • Introduces a large-scale benchmark and automated evaluation framework for verifying the correctness of code generated by large language models.

  2. Luo, M., Hao, A., Yan, Z., Cao, C., & Nguyen, Q. L. N. DiT-Serve: An Efficient Serving Engine for Diffusion Transformers. Under review at ICLR 2026.

    • Designs a scalable serving system for diffusion transformers with attention optimizations and continuous batching for high-throughput video generation.

Published Papers 📚

  1. Yan, Z., Dube, V., Heselton, J., Johnson, K., Yan, C., Jones, V., Blaskewicz Boron, J., & Shade, M. (2024). Understanding older people’s voice interactions with smart voice assistants: a new modified rule-based natural language processing model with human input. Frontiers in Digital Health, 6, 1329910.

    • DOI: 10.3389/fdgth.2024.1329910
    • Presents a hybrid NLP pipeline that incorporates human expertise to better analyze speech-to-text interactions between older adults and smart voice assistants.

  2. Jones, V. K., Yan, C., Shade, M. Y., Boron, J. B., Yan, Z., Heselton, H. J., Johnson, K., & Dube, V. (2024). Reducing Loneliness and Improving Social Support among Older Adults through Different Modalities of Personal Voice Assistants. Geriatrics (Basel, Switzerland), 9(2), 22.

    • DOI: 10.3390/geriatrics9020022
    • Evaluates how modality-specific interactions with personal voice assistants influence loneliness and perceived social support in older adults.

Working Papers 📝

VeriAgentBench: Benchmarking Project-Level Verifiable Code Agents in the Wild

In preparation for journal submission

Key Contributions:

  • Introduced a benchmark of 50 real-world repositories supporting repository-level verification of existing projects and verifiable generation from scratch.
  • Supervised by Dr. Dawn Song and Dr. Kaiyu Yang, I developed an automated evaluation pipeline measuring proof validity and functional correctness, revealing that state-of-the-art code agents achieve single-digit success rates on VeriAgentBench.

Adaptive Operations Management in Buildings: A Reinforcement Learning Approach for Operational Adaptability in Healthcare Facilities

In preparation for journal submission

Key Contributions:

  • Introduced a Reinforcement Learning-based framework to enable adaptive and integrated operations management in healthcare facilities, optimizing spatial, social, and operational performance through coordinated resource sharing.
  • Supervised by Dr. Yehuda Kalay and Dr. Davide Schaumann, I utilized deep reinforcement learning (RL) and simulation to develop a smart building management system for the Cardiac Catheterization Lab at St. Bernardine Medical Center, significantly enhancing facility adaptability and operational efficiency. The manuscript is in preparation for journal review.

For the most up-to-date information about my research work or to discuss potential collaborations, feel free to contact me.