Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Matched-Learning-Rate Analysis of Attention Drift and Transfer Retention in Fine-Tuned CLIP
Ruize Xia
CLIP adaptation can improve in-domain accuracy while degrading out-of-domain transfer, but comparisons between Full Fine-Tuning (Full FT) and LoRA are often confounded by different…
cs.LG2025
Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training
Qitao Tan, Sung-En Chang, Rui Xia +10
Zeroth-order (ZO) optimization is an emerging deep neural network (DNN) training paradigm that offers computational simplicity and memory savings. However, this seemingly promising…
cs.LG2024
Efficient Model Compression Techniques with FishLeg
Jamie McGowan, Wei Sheng Lai, Weibin Chen +7
In many domains, the most successful AI models tend to be the largest, indeed often too large to be handled by AI players with limited computational resources. To mitigate this, a…