Physical Intelligence publishes pi0.7 steerable robotic foundation model - 2026-04-16 - Research Publication - Physical Intelligence published pi0.7 as a steerable robotic foundation model with stronger generalization and task recombination abilities. The official release compares pi0.7 against specialist policies on laundry… - source: pi.website
Physical Intelligence publishes RLT research on efficient online RL for precise robot manipulation - 2026-03-19 - Research Publication - Physical Intelligence published RLT, an online reinforcement-learning method for precise robot manipulation. The work focuses on improving task performance efficiently through real-world policy updates. - source: pi.website
Physical Intelligence publishes Multi-Scale Embodied Memory for long-horizon VLA tasks - 2026-03-03 - Research Publication - Physical Intelligence published Multi-Scale Embodied Memory as a way to give VLA policies both short-term and long-term task memory. The official page frames MEM as enabling complex tasks lasting more than ten minutes… - source: pi.website
Physical Intelligence studies emergence of human-to-robot transfer in VLA models - 2025-12-16 - Research Publication - Physical Intelligence published research on how transfer from human videos to robotic tasks emerges as VLA models scale. The official page studies when human-video pretraining begins to help robotic task performance rather… - source: pi.website
Physical Intelligence publishes pi-star-0.6 VLA that learns from experience - 2025-11-17 - Research Publication - Physical Intelligence published pi-star-0.6 as a VLA trained with Recap-style reinforcement learning from autonomous robot experience. The release reports improvements on real-world application tasks such as box building… - source: pi.website
Physical Intelligence publishes real-time action chunking for high-latency VLA control - 2025-06-09 - Research Publication - Physical Intelligence published Real-Time Action Chunking as a method for keeping VLA-controlled robots precise while large models think over future action chunks. The official page frames the approach as an inpainting… - source: pi.website
Physical Intelligence publishes VLA training method for faster training and stronger generalization - 2025-05-28 - Research Publication - Physical Intelligence published a VLA training method focused on faster training, fast inference, and improved semantic generalization. The official page describes training with pi0-FAST action tokens, general web-data… - source: pi.website
Physical Intelligence publishes pi0.5 VLA for open-world generalization - 2025-04-22 - Research Publication - Physical Intelligence published pi0.5 as a VLA model focused on open-world generalization across messy homes and unstructured tasks. The official writeup emphasizes co-training on heterogeneous data so the model can… - source: pi.website
Physical Intelligence open-sources pi0 weights and openpi repository - 2025-02-04 - Research Publication - Physical Intelligence released code and model weights for pi0 through its experimental openpi repository. The release includes base pretrained checkpoints, fine-tuned checkpoints for platforms such as ALOHA and DROID, and… - source: pi.website
Physical Intelligence releases FAST robot action tokenizer for efficient VLA training - 2025-01-16 - Research Publication - Physical Intelligence published FAST, an efficient robot action tokenizer designed to connect high-frequency robot action chunks to autoregressive transformer training. FAST was trained on one million real robot action… - source: pi.website
Physical Intelligence introduces pi0 general-purpose robot foundation model - 2024-10-31 - Research Publication - Physical Intelligence introduced pi0 as its first generalist robot policy, combining a vision-language model backbone with action generation for dexterous robot control. The official release describes training across… - source: pi.website