Visual Generation

Practice Visual Generation in Python with research-based exercises, implementation guides, and tests on PaperLeet.

• 24. CLIP

  Align image and text representations using a symmetric in-batch contrastive objective.

  ICML 2021 · 1 exercises
• 57. SimCLR

  Implement NT-Xent over 2B anchors with positive-pair mapping, self masking, same-view negatives and temperature.

  ICML 2020 · 1 exercises
• 58. MoCo

  Build a consistent contrastive dictionary with a momentum encoder and cross-batch negative queue.

  CVPR 2020 · 1 exercises
• 30. Rotation Trick

  Use a frozen rotation and scale to construct vector-quantization surrogate gradients.

  ICLR 2025 Oral · 1 exercises
• 39. VAR

  Generate visual tokens from coarse to fine, predicting tokens within each scale in parallel.

  NeurIPS 2024 · 2 exercises
• 29. REPA

  Align intermediate generative features with a frozen semantic teacher.

  ICLR 2025 Oral · 1 exercises
• 17. Drifting Models

  Construct a drifting field that attracts real samples and repels generated samples, then train a generator against a stopped-gradient target.

  arXiv 2026 · 1 exercises
• 40. FD-Loss

  Estimate a larger feature population from historical statistics while backpropagating Fréchet distance through the current batch only.

  arXiv 2026 · 2 exercises