Tagged: pytorch
Showing 1–5 of 6 articles
Part 5: Planning in Latent Space Action-conditioned JEPA on the bouncing ball. Add direction as input to the predictor and the bimodal-future problem disappears. Brute-force MPC in embedding space drives a goal-image rollout. Read article Part 4: From Representations to World Models Running DINOv2 on a real image to see what a production joint-embedding encoder learns. Click a patch, get a similarity heatmap. No labels, no fine-tuning. Read article Part 3: Predict Embeddings, Not Pixels Joint embedding training, the representation collapse problem, and how Barlow Twins, VICReg, and LeJEPA's SIGReg fix it. Tested on the same bouncing-ball toy from Part 2. Read article Part 2: Why Pixel Prediction Goes Blurry Yann LeCun says generative models fail on video because the future is ambiguous. I tested the claim with a 700K-parameter PyTorch model on a synthetic bouncing ball. Read article Attention Is All You Need: Building the Original Transformer that Started the LLM Revolution Attention Is All You Need replaced RNNs with self-attention and changed everything. I built the original encoder-decoder transformer from scratch and trained it to translate English to French. Read article