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 similar instances closer and dissim ...
Paper Review - T-Cell Receptor meets VAE
T-cell receptors (TCR) bind to certain antigens found on abnormal cells. We can perform TCR engineering with VAEs.
Paper Review - Evolutionary Scale Modeling
ESM-1 and ESM-2 refer to protein language models developed by Facebook AI Research under the project name Evolutionary Scale Modeling (ESM). These models are designed to understand and predict various properties of proteins by leveraging the principles of language modeling in a manner similar to how models like GPT-3 process natural language.
Paper Review - AlphaFold2 and AlphaFold3
Let's try to figure out whats inside AlphaFold! AlphaFold can accurately predict structures of biomolecular interactions.
Paper Review - ProteinDT
ProteinDT is A Opensource Text-guided Protein Design Framework that uses Contrastive learning to align the two modalities.
Paper Review - Axial Transformer and MSA Transformer
The Axial Transformer is aimed at managing the complexity of high-dimensional data like images and videos, while The MSA transformer is focused on biological sequences and their alignments.