Repository
Models / Research
last0 · ZhuoyangLiu2005
LaST$_0$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
Overview
LaST$_0$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
Publisher purpose: [ICML 2026] LaST$_0$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
Review observation/action interfaces, checkpoints, robot embodiments and adaptation requirements. Repository code licensing does not automatically license weights or training data.
Project information
- Maintainer
- ZhuoyangLiu2005
- Primary language
- Python
- Repository code license
- Not specified
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2026-09-30
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- LaST<sub>0</sub>: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
- ✨ News ✨
- 📦 Installation
- Install Flash Attention 2
- =>> If you run into difficulty, try `pip cache remove flash_attn` first
- 🧩 Framework
Browse this resource’s categories
Explore related collections
Vision-language-action models ↗More in Models
Repository
Repository
Website
Research
OpenVLA-OFT
Fine-tuning tools for adapting OpenVLA action prediction.
Vision-language-action
Repository
Research
LIFT3D · PKU-HMI-Lab
Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
Robot policies