Bingcong Li
2 papers · Latest:
Machine Learning
Low-Rank Adaptation Redux for Large Models
This paper re-examines Low-Rank Adaptation (LoRA) through a signal processing lens, categorizing advancements in architecture, optimization, and applications.
2604.21905
Machine LearningZeroth-Order Optimization at the Edge of Stability
This paper characterizes the stability of zeroth-order optimization methods in deep learning, showing their unique dependence on the full Hessian spectrum.
2604.14669
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.