lucidrains/locoformer
LocoFormer - Generalist Locomotion via Long-Context Adaptation
LocoFormer helps robotics engineers train robots to adapt to new and unexpected conditions in real-time, even across different robot designs. It takes robot state information (like joint angles and velocities) and outputs the corresponding actions the robot should take to move or react. This is for researchers and engineers developing robust control systems for physical robots.
102 stars. Available on PyPI.
Use this if you are developing control systems for robots and need them to generalize across various physical embodiments and adapt to real-world disturbances without needing to be retrained.
Not ideal if you are working with purely simulated environments or do not require in-context adaptation for physical robot control.
Stars
102
Forks
5
Language
Python
License
MIT
Category
Last pushed
Mar 27, 2026
Commits (30d)
0
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lucidrains/locoformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action