Qiang Liu
  • About
  • Blog (current)
  • Publications
  • CV
  • NumericalMethods
  • •

  • Papers
  • •

  • DeepLearningNotes
  • •

  • paper-blog
  • •

  • technical-blog
  • Why your LoRA is not memory efficient?

    Although LoRA is a popular technique for finetuning, there are some subtle reasons in your LoRA implementation that might lead to increased computational overhead and memory usage. In this blog, we will explore these reasons and provide insights on how to optimize your LoRA implementation for better memory efficiency.

    19 min read   ·   February 25, 2026

    2026   ·   DeepLearningNotes   ·   technical-blog

  • Maximum likelihood estimation, Loss functions, and regularization

    From maximum likelihood estimation to loss functions and regularization in deep learning

    8 min read   ·   February 22, 2026

    2026   ·   DeepLearningNotes   ·   technical-blog

  • Introduction of Fourier Spectral Method

    A concise introduction to the Fourier spectral method for solving PDEs, including the basic idea of the spectral method, how to calculate linear and nonlinear terms in the spectral space, time integration methods, and the aliasing error caused by discretization.

    24 min read   ·   May 08, 2025

    2025   ·   NumericalMethods   ·   technical-blog

  • Towards Conflict-free training [ICLR 2025 Spotlight]

    A brief introduction on Conflict-free Inverse Gradients Method

    6 min read   ·   February 17, 2025

    2025   ·   Papers   ·   paper-blog

© Copyright 2026 Qiang Liu. Powered by Jekyll with al-folio theme. Hosted by GitHub Pages.