Robotics · Vision · Learning
Ran Cheng
Foundation models for robots·VLA·embodied AI·robot learning
I'm leading foundation-model research on robot learning — and I write deep, interactive explainers about how these systems work.
About
I'm the Research Executive Director at Primebot, where I lead a team building robotics foundation models — VLA, world models, reinforcement learning powered by universal reward functions, and memory & continual learning. Previously, at Ant Group, I led pretraining on ten-thousand-GPU clusters, post-training, and real-robot reinforcement learning; before that, I led an R&D department at Midea and scaled robotics products to over one million production units; and at Huawei Noah's Ark Lab, I built scene reconstruction and world-model systems for autonomous driving. I hold an M.Sc. from McGill University's Center for Intelligent Machines (advised by Gregory Dudek and David Meger) and a B.S. from Tongji University.
Writing
all posts →- 2026-07-29 Recurrent Memory: Write, Erase, Decay, Read
- 2026-07-27 Kernelization: The Licence to Move the Parentheses
- 2026-07-25 Linear Attention: Move the Parentheses
- 2026-07-23 The KV Cache: Why It's Allowed, and What It Costs
- 2026-06-26 Wind Tunnel Theory: The Engineering Endgame of Robot Learning
Research
publications →Selected work on vision-language-action models and robot-learning policies for manipulation, world models and embodied-AI benchmarks, and — from earlier — LiDAR perception, semantic scene completion, visual odometry, and monocular SLAM — see the publications page.