fix(evo1): finalize policy guide alignment

docs/source/evo1.mdx

@@ -26,7 +26,13 @@ The broader EVO1 project may include additional training scripts and dataset too
    pip install -e ".[evo1]"
    ```
 
-3. Install a `flash-attn` wheel only if it is compatible with your Python, PyTorch, CUDA, and GPU stack. EVO1 falls back to standard attention when `flash_attn` is not available.
+   For LIBERO evaluation, install the LIBERO extra as well:
+
+   ```bash
+   pip install -e ".[evo1,libero]"
+   ```
+
+3. Install a `flash-attn` wheel only if it is compatible with your Python, PyTorch, CUDA, and GPU stack. EVO1 falls back to standard attention when `flash_attn` is not available, but reproducing the official LIBERO checkpoint conversion result below requires the same FlashAttention path used by the original EVO1 checkpoint.
 
 EVO1 uses InternVL3 through the Hugging Face `transformers` remote-code path, so the first run may download the configured VLM checkpoint unless `policy.vlm_model_name` points to a local model directory.
 
@@ -61,6 +67,12 @@ Once a LeRobot-format EVO1 checkpoint is available, load it with:
 policy.path=your-org/your-evo1-checkpoint
 ```
 
+The converted LIBERO checkpoint used for this PR is available at:
+
+```python
+policy.path=javadcc/evo1-libero-lerobot
+```
+
 ## Training
 
 ### Stage 1
@@ -105,12 +117,19 @@ lerobot-train \
   --output_dir=./outputs/evo1_stage2
 ```
 
+By default, `policy.training_stage` reapplies the finetuning defaults for that stage. This is important when
+starting Stage 2 from a Stage 1 checkpoint, because the Stage 1 checkpoint config stores the VLM finetuning
+flags as disabled. These stage defaults take precedence over saved or manually supplied `policy.finetune_*`
+flags unless `policy.apply_training_stage_defaults=false`, so set that flag only when manually controlling
+every finetuning flag.
+
 ### Key Training Parameters
 
 | Parameter                                     | Default                  | Description                                                       |
 | --------------------------------------------- | ------------------------ | ----------------------------------------------------------------- |
 | `policy.vlm_model_name`                       | `OpenGVLab/InternVL3-1B` | InternVL3 checkpoint or local model directory                     |
 | `policy.training_stage`                       | `stage1`                 | `stage1` trains the action head; `stage2` finetunes VLM branches  |
+| `policy.apply_training_stage_defaults`        | `true`                   | Reapplies stage finetuning defaults after loading a checkpoint    |
 | `policy.vlm_num_layers`                       | `14`                     | Number of InternVL3 language layers kept for the policy           |
 | `policy.vlm_dtype`                            | `bfloat16`               | Requested VLM dtype                                               |
 | `policy.use_flash_attn`                       | `true`                   | Requests FlashAttention when installed; otherwise falls back      |
@@ -122,6 +141,41 @@ lerobot-train \
 | `policy.max_action_dim`                       | `24`                     | Action padding dimension                                          |
 | `policy.task_field`                           | `task`                   | Batch field used as the language prompt                           |
 
+## Results
+
+### LIBERO Object Checkpoint Conversion
+
+The checkpoint [javadcc/evo1-libero-lerobot](https://huggingface.co/javadcc/evo1-libero-lerobot)
+is the LeRobot-format conversion of the official EVO1 LIBERO checkpoint. The conversion was checked against
+the official EVO1 checkpoint with the same LIBERO Object initial states and action postprocessing.
+
+| Checkpoint                 | Suite           | Episodes        | Success Rate |
+| -------------------------- | --------------- | --------------- | ------------ |
+| Official EVO1 checkpoint   | `libero_object` | 10, one per task | 100%         |
+| LeRobot converted checkpoint | `libero_object` | 10, one per task | 100%         |
+
+For a fixed `libero_object` rollout, the official checkpoint and LeRobot checkpoint produced identical
+pixel embeddings, VLM fused tokens, normalized actions, and denormalized actions for the checked action step
+(`max_abs_diff=0.0`).
+
+The published checkpoint expects the raw LIBERO camera feature names
+`observation.images.agentview_image` and `observation.images.robot0_eye_in_hand_image`. To run the converted
+checkpoint with LeRobot LIBERO evaluation for the same one-episode-per-task setting, keep those camera names
+instead of the default `image`/`image2` mapping:
+
+```bash
+lerobot-eval \
+  --policy.path=javadcc/evo1-libero-lerobot \
+  --policy.device=cuda \
+  --env.type=libero \
+  --env.task=libero_object \
+  --env.camera_name_mapping="{agentview_image: agentview_image, robot0_eye_in_hand_image: robot0_eye_in_hand_image}" \
+  --env.observation_height=448 \
+  --env.observation_width=448 \
+  --eval.batch_size=1 \
+  --eval.n_episodes=1
+```
+
 ## References
 
 - [EVO1 repository](https://github.com/MINT-SJTU/Evo-1)

docs/source/policy_evo1_README.md

@@ -0,0 +1,18 @@
+# EVO1
+
+EVO1 is a Vision-Language-Action policy for robot control. The LeRobot
+integration uses an InternVL3 vision-language backbone with a flow-matching
+action head, and supports staged training through the standard LeRobot policy
+APIs.
+
+The upstream EVO1 project is available at
+[MINT-SJTU/Evo-1](https://github.com/MINT-SJTU/Evo-1).
+
+```bibtex
+@misc{evo1,
+  title = {EVO1},
+  author = {{MINT-SJTU}},
+  year = {2026},
+  howpublished = {\url{https://github.com/MINT-SJTU/Evo-1}},
+}
+```