Neural Network Surgery with Sets — mentioned by fxtentacle

Mon, 14 Oct 2024 14:24:38 GMT

To me, it seemed that the technique presented here was just a logical continuation of methods that OpenAI used when they trained the Dota agents: https://arxiv.org/pdf/1912.06719v1 And, arguably, Facebook's unsupervised pre-training for their multi-modal speech-to-text models is kind of the same idea as unsupervised pre-training for a multi-modal text-to-image diffuser. https://ai.meta.com/research/publications/wav2vec-2.0-a-fram...

Paper and discussion history. A mention is not an endorsement.

Neural Network Surgery with Sets · HackerPapers discussions

Neural Network Surgery with Sets — mentioned by fxtentacle