---
license: apache-2.0
pipeline_tag: robotics
tags:
  - robotics
  - vision-language-action
  - vla
  - imle
  - openpi
  - pi0.5
  - droid
  - franka
---

# IMLE-VLA checkpoints (IROS 2026)

Checkpoints for **IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies**
([paper](https://arxiv.org/abs/2609.10915), [project page](https://kianhk6.github.io/IMLE-VLA/),
[code](https://github.com/kianhk6/IMLE-VLA)).

<video controls muted playsinline width="100%" src="https://huggingface.co/kinster/IMLE-VLA/resolve/main/media/imle_vla_teaser.mp4"></video>

*Five-minute teaser: the setting, why regression collapses, why flow matching is slow and jerky, IMLE-VLA on the real robot, and how conditional IMLE works.*

IMLE-VLA replaces the 10-step flow-matching action head of π₀.₅ with a single-step generator trained with conditional
IMLE. Same frozen VLM backbone, one forward pass per action chunk, 55 Hz instead of 15 Hz on an NVIDIA L40S.

## Contents

| path | what | size |
|---|---|---|
| `droid/jax/57000/` | JAX (orbax) checkpoint of the real-robot DROID model: `params/` + `assets/droid/norm_stats.json`. Training config `16_horrizon_05_lr_2_factor_96_batch`, step 57000. Serve with `scripts/serve_policy.py policy:checkpoint`. | 6.6 GB |
| `droid/triton/` | The same weights converted for the single-step Triton engine (`pi05_imle_droid_57000.pkl`) plus `assets/droid/norm_stats.json`, the PaliGemma tokenizer and a provenance copy of the engine. This is the 55 Hz path used on the robot. | 6.3 GB |

The DROID model: π₀.₅ fine-tuned on DROID with the cIMLE objective (sample factor m = 2), frozen VLM, trained action
expert only, joint-position action space, 16-step action chunks, two camera views (one exterior + wrist). It is the policy
behind the real-robot experiments in the paper (Franka Emika Panda, four tabletop tasks, 55 Hz at execution horizon 12).

## Real-robot videos

Franka Emika Panda, both policies trained on DROID: π₀.₅ at 15 Hz versus IMLE-VLA at 55 Hz (the `droid/` checkpoint).

**Reactive task: pineapple on a moving plate.** A remote-controlled car moves the plate, so the target is in continuous motion.

| IMLE-VLA | π₀.₅ |
|---|---|
| <video controls muted playsinline width="100%" src="https://huggingface.co/kinster/IMLE-VLA/resolve/main/media/reactive_imle_vla_success.mp4"></video> | <video controls muted playsinline width="100%" src="https://huggingface.co/kinster/IMLE-VLA/resolve/main/media/reactive_pi05_fail.mp4"></video> |

**Static tasks** (side by side: π₀.₅ left, IMLE-VLA right)

Swap pineapple and cube

<video controls muted playsinline width="100%" src="https://huggingface.co/kinster/IMLE-VLA/resolve/main/media/swap_pineapple_cube.mp4"></video>

Pineapple in bowl

<video controls muted playsinline width="100%" src="https://huggingface.co/kinster/IMLE-VLA/resolve/main/media/pineapple_in_bowl.mp4"></video>

Pineapple in cabinet

<video controls muted playsinline width="100%" src="https://huggingface.co/kinster/IMLE-VLA/resolve/main/media/pineapple_in_cabinet.mp4"></video>

## Use

```bash
git clone --recurse-submodules https://github.com/kianhk6/IMLE-VLA.git && cd IMLE-VLA/openpi   # install per openpi/README.md
pip install -U huggingface_hub

# JAX checkpoint
huggingface-cli download kinster/IMLE-VLA --include "droid/jax/*" --local-dir ./ckpt
python scripts/serve_policy.py --env=DROID --port=8000 policy:checkpoint \
    --policy.config=16_horrizon_05_lr_2_factor_96_batch \
    --policy.dir=./ckpt/droid/jax/57000 \
    --policy.sample-kwargs='{"num_steps": 1}'

# Triton package (55 Hz)
huggingface-cli download kinster/IMLE-VLA --include "droid/triton/*" --local-dir ./ckpt
scripts/serve_triton.sh ./ckpt/droid/triton 16_horrizon_05_lr_2_factor_96_batch 0 8000 DROID
```

Then run the DROID robot client (`examples/droid/main.py --open_loop_horizon 12`) or score the served policy against
ground-truth DROID actions with `scripts/validate_triton_droid.py`. Both are documented in `openpi/README.md` and `openpi/docs/triton.md`.

## LIBERO

`libero/imle_vla_libero_h10_{spatial,object,goal,long,overall}` and `libero/imle_vla_libero_h30_{...}` hold LeRobot
checkpoints (`pretrained_model/`), per suite and overall, for execution horizon 10 and 30. Train and evaluate them with the
LeRobot code in the repository's [`lerobot/`](https://github.com/kianhk6/IMLE-VLA/tree/main/lerobot) folder.

## Citation

```bibtex
@inproceedings{Hosseinkhani2026IMLEVLAFS,
  title     = {{IMLE-VLA}: Fast Single-Step Action Generation for Vision-Language-Action Policies},
  author    = {Hosseinkhani, Kian and Peng, Qinhe and Shramko, George and Aghabozorgi, Mehran and
               Qian, Jianing and Engst, Tristan and Moazeni, Alireza and Jayaraman, Dinesh and Li, Ke},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year      = {2026},
  eprint    = {2609.10915},
  archivePrefix = {arXiv},
  url       = {https://arxiv.org/abs/2609.10915}
}
```

## License

Apache 2.0, like the [openpi](https://github.com/Physical-Intelligence/openpi) code and π₀.₅ checkpoints these weights
are fine-tuned from. The PaliGemma backbone is subject to the
[Gemma Terms of Use](https://ai.google.dev/gemma/terms).