[CVPR 2026]
PALM: Progress-Aware Policy Learning via Affordance Reasoning
for Long-Horizon Robotic Manipulation
Create and activate conda environment:
conda create -n palm python=3.10 -y
conda activate palmInstall PyTorch:
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117Install dependencies:
pip install git+https://github.com/openai/CLIP.git
pip install -r requirements.txtWe provide step-by-step guidance for running PALM in simulations and real-world experiments. Follow the specific instructions for a seamless setup.
For users aiming to train PALM from scratch or fine-tune it, we provide comprehensive instructions for environment setup, downstream task data preparation, training, and deployment.
This section details the pre-training process of PALM in real-world experiments, including environment setup, dataset preparation, and training procedures. Downstream task processing and fine-tuning are covered in Real-World (Quick Training w & w/o pre-training).
Relevant checkpoints are available on Google Drive.
If you find the project helpful for your research, please consider citing our paper:
@article{liu2026palm,
title={PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation},
author={Liu, Yuanzhe and Zhu, Jingyuan and Mo, Yuchen and Li, Gen and Cao, Xu and Jin, Jin and Shen, Yifan and Li, Zhengyuan and Yu, Tianjiao and Yuan, Wenzhen and others},
journal={arXiv preprint arXiv:2601.07060},
year={2026}
}