feat(policies): add LingBot-VA autoregressive video-action world model

Port the LingBot-VA policy (Wan2.2 dual-stream video+action world model) into
LeRobot, following the EO-1 / VLA-JEPA conventions. Covers inference, checkpoint
conversion, and predicted-video saving (training is deferred to a follow-up PR).

- Vendored Wan transformer/attention/flex/VAE/scheduler modules (key names preserved
  for near-identity conversion); torch SDPA default, flashattn/flex lazy-guarded.
- LingBotVAConfig (registered "lingbot_va") + processor with fixed-quantile action
  unnormalization; full dual-stream sampling loop with CFG, two flow-matching
  schedulers and KV cache, mapped onto select_action with observed-keyframe feedback.
- convert_lingbot_va_checkpoints.py (libero/robotwin variants): bundles the ~5B
  transformer, lazy-pulls the frozen VAE+UMT5 from the source repo.
- Predicted-video plumbing in lerobot_eval (predicted_frames_callback; opt-in via
  --policy.save_predicted_video) and ConstantWithWarmupSchedulerConfig.
- pyproject: widen diffusers-dep to <0.37, add lingbot_va + imageio-dep extras,
  add lingbot_va and (missing) eo1 to `all`.
- Factory + policies/__init__ wiring, docs page + toctree, and tests.

Note: the LIBERO success-rate correctness gate must be validated on a CUDA GPU
with the converted checkpoint.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

pyproject.toml

@@ -146,7 +146,8 @@ grpcio-dep = ["grpcio==1.73.1", "protobuf>=6.31.1,<6.32.0"]
 can-dep = ["python-can>=4.2.0,<5.0.0"]
 peft-dep = ["peft>=0.18.0,<1.0.0"]
 scipy-dep = ["scipy>=1.14.0,<2.0.0"]
-diffusers-dep = ["diffusers>=0.27.2,<0.36.0"]
+diffusers-dep = ["diffusers>=0.27.2,<0.37.0"]
+imageio-dep = ["imageio[ffmpeg]>=2.34.0,<3.0.0"]
 qwen-vl-utils-dep = ["qwen-vl-utils>=0.0.11,<0.1.0"]
 matplotlib-dep = ["matplotlib>=3.10.3,<4.0.0", "contourpy>=1.3.0,<2.0.0"] # NOTE: Explicitly listing contourpy helps the resolver converge faster.
 pyserial-dep = ["pyserial>=3.5,<4.0"]
@@ -218,6 +219,10 @@ xvla = ["lerobot[transformers-dep]"]
 eo1 = ["lerobot[transformers-dep]", "lerobot[qwen-vl-utils-dep]"]
 hilserl = ["lerobot[transformers-dep]", "lerobot[dataset]", "gym-hil>=0.1.13,<0.2.0", "lerobot[grpcio-dep]", "lerobot[placo-dep]"]
 vla_jepa = ["lerobot[transformers-dep]", "lerobot[diffusers-dep]", "lerobot[qwen-vl-utils-dep]"]
+# LingBot-VA needs the Wan2.2 stack (AutoencoderKLWan z_dim=48 + WanTransformer3DModel config schema),
+# which only exists in diffusers>=0.36. Pin the floor explicitly so a standalone `lerobot[lingbot_va]`
+# install can't resolve to a pre-Wan2.2 diffusers via the looser diffusers-dep floor.
+lingbot_va = ["lerobot[transformers-dep]", "diffusers>=0.36.0,<0.37.0", "lerobot[imageio-dep]"]
 
 # Features
 async = ["lerobot[grpcio-dep]", "lerobot[matplotlib-dep]"]
@@ -284,6 +289,8 @@ all = [
     "lerobot[xvla]",
     "lerobot[hilserl]",
     "lerobot[vla_jepa]",
+    "lerobot[eo1]",
+    "lerobot[lingbot_va]",
     "lerobot[async]",
     "lerobot[dev]",
     "lerobot[test]",
@@ -375,6 +382,9 @@ ignore = [
 # E402: conditional-import guards (TYPE_CHECKING / is_package_available) must precede the imports they protect
 "src/lerobot/scripts/convert_dataset_v21_to_v30.py" = ["E402"]
 "src/lerobot/policies/wall_x/**" = ["N801", "N812", "SIM102", "SIM108", "SIM210", "SIM211", "B006", "B007", "SIM118"] # Supprese these as they are coming from original Qwen2_5_vl code TODO(pepijn): refactor original
+# Vendored Wan2.2 / LingBot-VA model code uses tensor-dimension names (B, F, H, W) and `F` for
+# torch.nn.functional; keep the upstream naming to make diffing against upstream tractable.
+"src/lerobot/policies/lingbot_va/**" = ["N803", "N806", "N812", "SIM102"]
 
 [tool.ruff.lint.isort]
 combine-as-imports = true