McGill University

2 Posts

The Big Picture and the Details: I-JEPA, or how vision models understand the relationship between parts and the whole

A novel twist on self-supervised learning aims to improve on earlier methods by helping vision models learn how parts of an image relate to the whole.

McGill University

Visual Strategies for RL: Plan2Vec helps reinforcement learning with complex tasks.

Reinforcement learning can beat humans at video games, but humans are better at coming up with strategies to master more complex tasks. New work enables neural networks to connect the dots.

McGill University

The Big Picture and the Details: I-JEPA, or how vision models understand the relationship between parts and the whole

Visual Strategies for RL: Plan2Vec helps reinforcement learning with complex tasks.

Subscribe to The Batch