-
LoRA as Parametric Memory: a failed experiment
I tried writing conversation facts into model weights via LoRA fine-tuning. The accuracy was dismal and temporal questions were completely unanswerable.
-
AI as Research Copilot
How AI evolved from coding assistant to research partner in my workflow.
-
Linear Attention 在 GPU 上到底慢在哪
Linear attention 在 GPU 上表现不好是直觉，不是结论。我们做了一组实验，然后被学长推翻了一半。这篇文章记录这个过程。
-
ForgeHLS and DiffHLS: why I built them, and why HLS still feels like a trap
A personal note on building a large-scale HLS dataset, pushing DiffHLS forward, and why I remain skeptical about HLS as a long-term research direction in 2026.
-
Notes on Proofs, Arguments, and Zero-Knowledge
Tags machine learning, security, privacy, and mobile computing. Guided by Liyao Xiang