Skip to content
Only First party#Physical Intelligence
Oct 13Tue
  1. Physical Intelligence62

    Physical Intelligence opens Pi API beta, offering π model training and inference

    Physical Intelligence has opened the Pi API beta, allowing developers to upload data, fine-tune π models on the company-managed compute and infrastructure, and then run inference through a hosted gateway; the current interface already offers more data-efficient fine-tuning and improvement capabilities.

    Why it matters: Pi API brings data upload, fine-tuning, and hosted inference into one ready-made pipeline, helping readers weigh building their own machine learning infrastructure against calling the API directly.

Apr 16Thu
  1. Physical Intelligence77

    Physical Intelligence releases steerable general-purpose robot model π0.7, demonstrating compositional generalization

    Physical Intelligence has released the general-purpose robot model π0.7, which it says can perform a variety of dexterous manipulations with speed and robustness comparable to fine-tuned specialized models, and shows preliminary signs of compositional generalization on tasks not seen in its training data.

    Why it matters: The article uses two specific experiments, an air fryer and folding clothes with a UR5e, to show the actual performance of compositional generalization and cross-embodiment transfer, making it easier to judge the gap between general-purpose and specialized models.

Mar 19Thu
  1. Physical Intelligence60

    Physical Intelligence proposes RLT: efficient online reinforcement learning for fine manipulation

    Physical Intelligence proposes a new method called RL tokens (RLT), in which a vision-language-action model (VLA) outputs a special token to interface with a lightweight online reinforcement learning policy, improving the speed and success rate of fine manipulation phases with only a small amount of real data.

    Why it matters: The original clearly explains the interface design between the VLA and lightweight online reinforcement learning and provides speedup data on four tasks, so readers can assess whether this type of method applies to their own fine manipulation tasks.

Mar 3Tue
  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.

Feb 24Tue
  1. Physical Intelligence74

    Physical Intelligence proposes a physical intelligence layer and publishes π 0.6 deployment data from Weave and Ultra

    In a blog post, Physical Intelligence argues that robots need a reusable physical intelligence layer, and it published real-world deployment data from partners Weave and Ultra using π 0.6.

    Why it matters: The two deployers provided comparative data on autonomy rates, missed grasps, and throughput, making it easier to judge the practical gains that foundation model iterations bring in real-world settings.

Dec 22Mon
  1. Physical Intelligence64

    Physical Intelligence fine-tunes π 0.6 to take on five Robot Olympics tasks, winning three golds and two silvers

    By fine-tuning its latest π 0.6 model, Physical Intelligence achieved preliminary solutions for the gold-medal tasks in 3 of the five everyday manipulation challenges in the Robot Olympics proposed by Benjie Holson, and reached silver-medal level in the remaining 2, with an average success rate of 52% and task progress of 72%.

    Why it matters: Using the same set of externally proposed everyday manipulation tasks to compare performance with and without robot pretraining lets readers judge the practical value of foundation-model pretraining for manipulation skills.

Dec 16Tue
  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.

Nov 17Mon
  1. Physical Intelligence74

    Physical Intelligence releases π*0.6, a VLA model that learns from experience

    Physical Intelligence released the VLA model π*0.6. After training with its Recap (RL with Experience & Corrections via Advantage-conditioned Policies) method, throughput on some of the hardest tasks more than doubled, and the failure rate can be reduced to half of the original or lower.

    Why it matters: The original article explains how compounding errors arise in VLA under imitation learning and presents a training approach that uses expert corrections and autonomous experience for reinforcement learning.