Event
Qiyuan Robot Releases PrimeSim World Model Simulator
4 reports · 3 sources
Qiyuan Robot (Qiyuan Embodied Research Center) has released PrimeSim, a world model simulator for robotic manipulation tasks. Built on a pretrained video generation model and adapted through two stages—mid-training and post-training—it is used for policy validation and reinforcement learning. Qiyuan says that in tests, using PrimeSim for reinforcement learning raised policy success rates from 61.7% to 73.2%. Regarding benchmark results, earlier reports said PrimeSim topped the WorldSimProbe LIBERO leaderboard; later reports said it ranked first on EWMBench with a composite score of 6.09, and took first place in three of five WorldSimProbe evaluations: global trajectory coverage, action-source behavior preservation, and interaction dynamics. According to Machine Heart, PrimeSim's weights, inference code, and training code will soon be open-sourced.
Report timeline
- Qiyuan Robotics launches PrimeSim world model, tops WorldSimProbe LIBERO leaderboard
On October 30, Qiyuan Robotics launched PrimeSim, a world-model simulator for robot training, and topped the WorldSimProbe LIBERO leaderboard. The simulator builds an interactive, trial-and-error, continuously learning virtual world for robots, supporting policy validation and reinforcement learning. In testing, reinforcement learning with it raised policy success rate from 61.7% to 73.2%.
36Kr Embodied Intelligence ·
- Qiyuan Robotics launches PrimeSim world model, tops WorldSimProbe LIBERO leaderboard
Qiyuan Robotics launched PrimeSim, a world-model simulator for robot training, on October 30 and topped the WorldSimProbe LIBERO leaderboard. The simulator builds an interactive, trial-and-error-friendly, continuously learning virtual world for robots, used for policy validation and reinforcement learning. In testing, reinforcement learning with it raised policy success rates from 61.7% to 73.2%.
36氪 · 微信公众号 ·
- Qiyuan releases PrimeSim world-model simulator, tops EWMBench and WorldSimProbe
The Qiyuan Embodied Research Center has released PrimeSim, a world-model simulator for robot manipulation tasks, built by adapting a pretrained video generation model through mid-training and post-training stages. It ranks first on EWMBench with an overall score of 6.09, and took first place in three of five WorldSimProbe evaluations: global trajectory coverage, action-source behavior preservation, and interaction dynamics.
机器之心 · 微信公众号 ·
- Qiyuan Robotics launches PrimeSim world model and tops WorldSimProbe LIBERO leaderboard
Qiyuan Robotics has launched PrimeSim, a world-model simulator for robot training, and topped the WorldSimProbe LIBERO leaderboard. PrimeSim builds an interactive, trial-and-error, continuously learning virtual world for robots, used for policy validation and reinforcement learning. In tests, reinforcement learning with it raised policy success rate from 61.7% to 73.2%.
36Kr Embodied Intelligence ·