| --- |
| license: other |
| license_name: slim-license |
| license_link: https://github.com/kzz1031/SLIM/blob/main/LICENSE |
| library_name: slim-policy |
| tags: |
| - robotics |
| - robot-manipulation |
| - flow-matching |
| - self-supervised-learning |
| - calvin |
| --- |
| |
| # SLIM for CALVIN |
|
|
| This repository contains the released SLIM Stage 2 epoch-15 policy checkpoint |
| for the CALVIN ABC-D benchmark. The Stage 2 run was trained for 40 epochs, and |
| epoch 15 was selected for the reported result. SLIM is a compact latent |
| interaction policy for robot manipulation. |
|
|
| ## Checkpoint |
|
|
| - Stage 1: action-grounded masked trajectory prediction, IDM:FDM = 0.125:1 |
| - Stage 1 duration: 3 epochs |
| - Stage 2: flow-matching policy training for 40 epochs; this release uses the |
| checkpoint saved at epoch 15 |
| - Action horizon and execution stride: 12 |
| - State/action dimensions: 15/7 |
|
|
| The checkpoint is a plain PyTorch `state_dict` and loads directly with |
| [SLIM](https://github.com/kzz1031/SLIM). |
|
|
| ## Results |
|
|
| The paper result on 1,000 CALVIN ABC-D long-horizon sequences is an average |
| successful sequence length of **4.556**. Success rates at sequence lengths 1 |
| through 5 are **99.3%, 96.7%, 92.3%, 87.1%, and 80.2%**. |
|
|
| A fresh evaluation of the released package produced an average successful |
| sequence length of **4.578**, with success rates of **99.9%, 96.4%, 92.2%, |
| 88.0%, and 81.3%**. Machine-readable results are included under `evaluation/`. |
|
|
| ## Usage |
|
|
| Install SLIM and configure the DINOv2 and T5 paths as described in the SLIM |
| README. Then start a policy server from the SLIM repository root: |
|
|
| ```bash |
| python -m slim.serving.server \ |
| --checkpoint /path/to/SLIM-CALVIN/checkpoints/epoch_15_pytorch_model.pt \ |
| --port 10093 \ |
| --bf16 |
| ``` |
|
|
| Keep the included `config.yaml` and `action_stats.json` in the repository root. |
| See `checkpoint_manifest.json` for hashes and the exact SLIM revision. |
|
|
| ## Limitations |
|
|
| This checkpoint is intended for research evaluation in CALVIN-compatible |
| simulation environments. It should not be deployed on physical robots without |
| task-specific safety validation and action-bound checks. |
|
|
