#Self-Supervised Learning
5 articles with this tag
LeVJEPA Cuts Video Pretraining Cost 20x
LeVJEPA trains a single video encoder with SIGReg, matching V-JEPA 2 at 5.6 to 20.8x less compute and beating image-pretrained DINOv2 on motion by ~2x.
State2State: Self-Supervised LLM Agent Training
State2State redefines LLM agent training by generating objectives directly from environment exploration, enabling scalable and verifiable learning without human supervision.
Yann LeCun on World Models and the AI Revolution
AI pioneer Yann LeCun discusses how 'World Models' are key to the next AI revolution, emphasizing prediction, planning, and learning from real-world data.
Yann LeCun Pushes AI Beyond Language Models
Yann LeCun is championing a new AI architecture, JEPA, that moves beyond language models to learn world representations and predict future states, aiming for more robust AI.
New EB-JEPA Library Simplifies AI World Models
Meta AI's new EB-JEPA library offers accessible, single-GPU implementations for advanced AI world models, covering image, video, and planning tasks.