- formatting
- images
- links
- math
- code
- blockquotes
- external-services
•
•
•
•
•
•
-
Paper Review - Modality Gap and Alignment in Multi-modal Contrastive Learning
Contrastive learning is a popular self-supervised learning technique that has shown remarkable success in training deep neural networks. The core idea behind contrastive learning is to learn representations that are not only discriminative but also invariant to various transformations. This is achieved by contrasting positive and negative samples in the embedding space.
-
Notes on Score-Based Generative Models
My personal notes for studying diffusion models. Watching Dome's youtube video to learn.
-
Paper Review - PDAE, DisDiff and InfoDiffusion
Literature review on Unsupervised Representation Learning in diffusion models.
-
Paper Review - ColorPeel
An interesting paper from ECCV2024. It talks about the color and shape disentanglement on Text-to-Image models. The solution is simple yet effective.
-
Paper Review - Disentangled Contrastive Learning on Graphs
Revisit Contrastive learning
Contrastive learning is an instance-wise discriminative approach that aims at making