Search Results for author:
Found 2 papers, 0 papers with code
Compound Tokens: Channel Fusion for Vision-Language Representation Learning
We concatenate all the compound tokens for further processing with multimodal encoder.
Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks
By selecting a weight among a fixed set of random values for each individual connection, our method uncovers combinations of random weights that match the performance of traditionally-trained networks of the same capacity.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
