Yann LeCun提出预测抽象表示缩小AI数据需求差距
AI needs vastly more data than we do. One idea might close the gap: don't predict raw signals (tokens), predict your own abstract latent representation (JEPA, data2vec).
With @DanKorchinski @MatthieuWyart, on a toy model, we prove how much that helps: the gap is exponential.
🧵 https://t.co/I51Q6Jwiqr
With @DanKorchinski @MatthieuWyart, on a toy model, we prove how much that helps: the gap is exponential.
🧵 https://t.co/I51Q6Jwiqr