Skip to content
Only First party#Other
  1. Physical Intelligence78

    Physical Intelligence proposes MEM, enabling π0.6's VLA to remember long-horizon tasks of up to 15 minutes

    Physical Intelligence proposed a method called Multi-scale Embodied Memory (MEM) that provides vision-language-action models (VLAs) with both short-term and long-term memory, enabling the model to complete tasks lasting up to 15 minutes, such as cleaning an entire kitchen or making a grilled cheese sandwich from scratch.

    Why it matters: The article identifies memory mechanisms as the bottleneck for long-horizon tasks and presents a dual-scale design that stores video for the short term and language for the long term, an approach that can be transferred to other work.

  1. Physical Intelligence73

    Physical Intelligence: VLA models show human-to-robot transfer as robot data scale grows

    Physical Intelligence research found that in generalization scenarios where only human demonstrations appear, fine-tuning π0.5 with human first-person videos mixed into robot data alone improved policy performance by about 2x, without using any explicit transfer learning mechanism.

    Why it matters: Experiments show that merely mixing human videos into fine-tuning improves the policy by about 2x on scenarios with purely human demonstrations, and this capability emerges as pretraining robot data scale grows.

You’re all caught up