Self-Supervised Learning

OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation featured image

Multimodal Learning

OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation

OSKAR is a self-supervised multimodal foundation model that learns in the latent space by predicting masked multimodal features.

mohamed-abdelfattah

• Dec 1, 2025 • 1 min read

S-JEPA: Joint Embedding Predictive Architecture for Self-Supervised Skeletal Action Recognition featured image

Self-Supervised Learning

S-JEPA: Joint Embedding Predictive Architecture for Self-Supervised Skeletal Action Recognition

S-JEPA is an instantiation of JEPA for self-supervised skeletal action recognition.

mohamed-abdelfattah

• Nov 10, 2025 • 1 min read