Update README.md

README.md

@@ -12,11 +12,11 @@ tags:
 
 [**Paper**](https://huggingface.co/papers/2602.09021) | [**Project Page**](https://mmlab.hk/research/kai0) | [**GitHub Repository**](https://github.com/OpenDriveLab/KAI0)
 
-$\\chi_{0}$ (pronounced **kai0**) is a resource-efficient framework designed to achieve production-level robustness in robotic manipulation. It addresses the systematic inconsistency and distributional shift among human demonstrations, the inductive bias learned by the policy, and test-time execution, which are primary bottlenecks to real-world robustness in multi-stage tasks.
+$\chi_{0}$ (pronounced **kai0**) is a resource-efficient framework designed to achieve production-level robustness in robotic manipulation. It addresses the systematic inconsistency and distributional shift among human demonstrations, the inductive bias learned by the policy, and test-time execution, which are primary bottlenecks to real-world robustness in multi-stage tasks.
 
 ## Technical Pillars
 
-The $\\chi_{0}$ approach is built upon three technical pillars:
+The $\chi_{0}$ approach is built upon three technical pillars:
 
 1.  **Model Arithmetic:** A weight-space merging strategy that efficiently soaks up diverse distributions from different demonstrations, varying from object appearance to state variations. This aggregates knowledge without architectural complexity.
 2.  **Stage Advantage:** A stage-aware advantage estimator that provides stable, dense progress signals, overcoming the numerical instability of prior non-stage approaches.
@@ -24,7 +24,7 @@ The $\\chi_{0}$ approach is built upon three technical pillars:
 
 ## Performance
 
-$\\chi_{0}$ enables two sets of dual-arm robots to collaboratively orchestrate long-horizon garment manipulation tasks, including flattening, folding, and hanging different clothes. The method exhibits high-reliability autonomy, capable of running the system from an arbitrary initial state for consecutive 24 hours non-stop. Experiments validate that $\\chi_{0}$ surpasses the state-of-the-art $\\pi_{0.5}$ in success rate by nearly 250%, achieved with only 20 hours of data and 8 A100 GPUs.
+$\chi_{0}$ enables two sets of dual-arm robots to collaboratively orchestrate long-horizon garment manipulation tasks, including flattening, folding, and hanging different clothes. The method exhibits high-reliability autonomy, capable of running the system from an arbitrary initial state for consecutive 24 hours non-stop. Experiments validate that $\\chi_{0}$ surpasses the state-of-the-art $\\pi_{0.5}$ in success rate by nearly 250%, achieved with only 20 hours of data and 8 A100 GPUs.
 
 ## License
 
@@ -32,7 +32,7 @@ The code in the repository is licensed under the Apache 2.0 license. The data an
 
 ## Citation
 
-If you find $\\chi_{0}$ useful in your research, please consider citing:
+If you find $\chi_{0}$ useful in your research, please consider citing:
 
 ```bibtex
 @article{sima2026kai0,