← Search

Yuankun Zu

2 accepted papers

2025

Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks

AAAI 2025technical

In practical applications, it is often necessary to transfer knowledge from large pretrained models to small ones with various architectures for tackling different tasks. The Learngene framework, proposed recently, firstly extracts one compact module termed as learngene from a large well-trained mod…

Cited by 0SourcePDFScholar
2024

Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation

NeurIPS 2024poster

In practical scenarios, it is necessary to build variable-sized models to accommodate diverse resource constraints, where weight initialization serves as a crucial step preceding training. The recently introduced Learngene framework firstly learns one compact module, termed learngene, from a large w…

Cited by 4SourcePDFScholar