Xiao Ma (@yusufma555) on X

Xiao Ma on X: "I've been working on deformable object manipulation since my PhD. It was totally a nightmare years ago and my PhD advisor was telling me not to work on it for my own good. Today, at ByteDance Seed, we are dropping GR-RL, a new VLA+RL system that manages long-horizon precise"

I've been working on deformable object manipulation since my PhD. It was totally a nightmare years ago and my PhD advisor was telling me not to work on it for my own good. Today, at ByteDance Seed, we are dropping GR-RL, a new VLA+RL system that manages long-horizon precise dexterous manipulation of deformable objects. This is probably the first real-world RL system to make a robot: ✅ Lace up your shoes end to end ✅ Hit millimeter tolerance repeatedly ✅ Recover from mistakes (See video!) ✅ And complete continuous shoelace threading on a real bimanual platform 📈 Success rate: ↑ from 45.7% → 83.3% Yes, robots can now actually do this. Project page: seed.bytedance.com/en/gr_rl ArXiv: arxiv.org/abs/2512.01801
Why “shoelace threading” matters 🤔 This task is probably one of the most challenging household robotics tasks in terms of precision: 💥 Soft-body chaos – laces deform every frame 💥 Millimeter precision – 1–2 mm slip = total failure 💥 Long-horizon manipulation – hundreds of
Two killers of imitation learning (IL): (1) Human demos are NOT optimal Humans hesitate, retry, fix mistakes mid-trajectory. IL blindly copies ALL of it — including the bad parts. (2) Training vs Deployment Misalignment VLA models output actions. To prevent jitter, robots
The Idea: If imitation is broken, then: Let the robot learn from its own experience. GR-RL = ⭐️ Offline RL (data filtering) ⭐️ Symmetry augmentation ⭐️ Online closed-loop Real-World Reinforcement Learning All on top of a single VLA foundation model. Just RGB, proprioception,
Offline Stage — Filter the human flaws We train a Critic Transformer via distributional RL: ⭐️ Detects “value drops” when the operator hesitates or messes up ⭐️ Slices every trajectory into high-value vs low-value segments ⭐️ Retains only the cleanest expert behavior Effect:
Morphological Symmetry Augmentation Our bi-manual robot is left–right symmetric. So we mirror EVERYTHING: 🚀 RGB 🚀 Proprioception 🚀 Actions 🚀 Language Instructions Data size doubles. Spatial reasoning robustness skyrockets. → 72.7% success.
Online Stage — Real-World Steering RL Now the robot learns ON THE PHYSICAL PLATFORM. But direct exploration in joint space causes dangerous jitter and is inefficient — you need millimeter accuracy. So GR-RL explores in the latent noise space: A tiny 51.5M-param noise-predictor
The Result: Final performance: 83.3% success over continuous shoelace threading. The surprising part? GR-RL learns to: 🔥 retry when the lace slips 🔥 reposition the lace when the initial pose is bad 🔥 "self-correct" mid-task instead of freezing This is the behavior you
GR-RL proves something: IL is inherently limited, and we can do things previously thought impossible by purely visuo-motor control simply making it RL. The future direction is clear: distill RL-enhanced behavior back into the foundation VLA, forming a self-improving,
Wow! I love how it naturally pulls the shoe closer so that it can complete the task easier. Awesome work!