avatar

David H. Yang

Ph.D. Student
Rensselaer Polytechnic Institute
yangd13@rpi.edu


About Me

I’m currently a third year Ph.D. student at Rensselaer Polytechnic Institute, advised by Dr. Mohammad Amiri and Dr. Tomek Strzalkowski. I work on building scalable AI systems that enable deeper human-AI collaboration and understanding over long-term interactions. My recent research lies in the efficiency and long-context memory capabilities of LLMs, with the broader goal of developing lifelong learning systems that can adapt to dynamic, evolving environments.

Previously, I completed my Master’s degree in Computer Science and Bachelors in Electrical Engineering from the University of Toronto.

Before embarking on my PhD journey, I co-founded two startup companies with a strong focus on AI technology.

Addressing construction estimation needs at ML Estimation.

Immersify yourself and create stories using Story Crafter.

News

Publications

  1. ACL
    ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
    David H. Yang, Yuxuan Zhu, Mohammad Mohammadi Amiri, Keerthiram Murugesan, Tejaswini Pedapati, Subhajit Chaudhury, Pin-Yu Chen
    Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, ACL 2026
    PDF

  2. ACL
    OjaKV: Context-Aware Online Low-Rank KV Cache Compression with Oja's Rule
    Yuxuan Zhu*, David H. Yang*, Mohammad Mohammadi Amiri, Keerthiram Murugesan, Tejaswini Pedapati, Pin-Yu Chen
    Findings of the Association for Computational Linguistics, ACL 2026
    PDF

  3. COLM
    SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching
    Yuxuan Zhu, Ali Falahati, David H. Yang, Mohammad Mohammadi Amiri
    Conference on Language Modeling, COLM 2025
    PDF

  4. Sparse Gradient Compression for Fine-Tuning Large Language Models
    David H. Yang, Mohammad Mohammadi Amiri, Tejaswini Pedapati, Subhajit Chaudhury, Pin-Yu Chen
    Workshop on Sparsity in LLMs, ICLR 2025
    PDF

  5. Sci. Adv.
    Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data
    Aparna Balagopalan, David Madras, David H. Yang, Dylan Hadfield-Menell, Gillian K Hadfield, Marzyeh Ghassemi
    Science Advances (Sci. Adv.), 2023.
    PDF

Services

Conference Reviewers