Search Results for author:
Found 2 papers, 1 papers with code
GIFT: Generative Interpretable Fine-Tuning Transformers
For the latter, in contrast to the prior art that directly introduce new model parameters (often in low-rank approximation form) to be learned in fine-tuning with downstream data, we propose a method for learning to generate the fine-tuning parameters.
Transforming Transformers for Resilient Lifelong Learning
To our knowledge, it is the first attempt of lifelong learning with ViTs on the challenging VDD benchmark.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
