4 citations · 10 across the 10 of their papers we have counts for
7 papers · 1 filter
Residual Feature Integration is Sufficient to Prevent Negative Transfer
Yichen Xu, Ryumei Nakada, Linjun Zhang +1
Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representati…
A Theoretical Framework for Prompt Engineering: Approximating Smooth Functions with Transformer Prompts
Ryumei Nakada, Wenlong Ji, Tianxi Cai +2
Prompt engineering has emerged as a powerful technique for guiding large language models (LLMs) toward desired responses, significantly enhancing their performance across diverse t…
SFT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
Xinyu Yang, Jixuan Leng, Geyang Guo +5
Current PEFT methods for LLMs can achieve either high quality, efficient training, or scalable serving, but not all three simultaneously. To address this limitation, we investigate…
PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers
Yibo Zhong, Haoxiang Jiang, Lincan Li +5
Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-…
Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
Alyssa Huang, Peihan Liu, Ryumei Nakada +2
The surge in multimodal AI's success has sparked concerns over data privacy in vision-and-language tasks. While CLIP has revolutionized multimodal learning through joint training o…
Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data
Ryumei Nakada, Halil Ibrahim Gulluk, Zhun Deng +3
Language-supervised vision models have recently attracted great attention in computer vision. A common approach to build such models is to use contrastive learning on paired data a…
The Power of Contrast for Feature Learning: A Theoretical Analysis
Wenlong Ji, Zhun Deng, Ryumei Nakada +2
Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical succ…