Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
Yu-Ang Lee, Ching-Yun Ko, Pin-Yu Chen +1
Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model (LLM) fine-tuning. Building on this paradigm, recent studies have proposed alternative init…
cs.LG2025
Rethinking the shape convention of an MLP
Meng-Hsi Chen, Yu-Ang Lee, Feng-Ting Liao +1
Multi-layer perceptrons (MLPs) conventionally follow a narrow-wide-narrow design where skip connections operate at the input/output dimensions while processing occurs in expanded h…