Search Results for author:
Found 3 papers, 1 papers with code
Merge to Mix: Mixing Datasets via Model Merging
Our key insight is that merging models individually fine-tuned on each dataset in a mixture can effectively serve as a surrogate for a model fine-tuned on the entire mixture.
Rethinking VLMs and LLMs for Image Classification
Visual Language Models (VLMs) are now increasingly being merged with Large Language Models (LLMs) to enable new capabilities, particularly in terms of improved interactivity and open-ended responsiveness.
Frivolous Units: Wider Networks Are Not Really That Wide
We identify two distinct types of "frivolous" units that proliferate when the network's width is increased: prunable units which can be dropped out of the network without significant change to the output and redundant units whose activities can be expressed as a linear combination of others.
