Add pipeline tag and links to paper, project, and code

This PR adds the `pipeline_tag: robotics` to the metadata so the model is properly categorized and discoverable. It also adds links to the paper, project page, and code repository in the model card content, making it easier for users to access the original research and implementation.

README.md

@@ -1,11 +1,12 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen3.5-2B
+license: apache-2.0
+pipeline_tag: robotics
 tags:
-  - robotics
-  - vision-language-action
-  - humanoid
-  - lambda0
+- robotics
+- vision-language-action
+- humanoid
+- lambda0
 ---
 
 # λ₀ Midtrain (100k)
@@ -14,6 +15,12 @@ This is the **Stage II mid-training checkpoint** for λ₀. It provides the star
 
 The model builds on [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) and learns from robot-aligned human demonstrations.
 
+## Links
+
+- **Paper:** [λ₀: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation](https://huggingface.co/papers/2610.18950)
+- **Project page:** [Lambda Humanoid](https://lambdahumanoid.github.io/)
+- **Code:** [OpenLambda repository](https://github.com/LambdaHumanoid/openlambda)
+
 ## Post-training
 
 The Stage III post-training recipe is being prepared in the [OpenLambda source repository](https://github.com/LambdaHumanoid/openlambda). Follow that recipe when it is released to adapt this checkpoint to your robot tasks.
@@ -24,4 +31,4 @@ The pretraining and mid-training datasets are not included. This checkpoint is n
 
 The files include the model weights and the configuration needed to load them. The weight tensor file is unchanged from the Stage II checkpoint at step 100,000.
 
-The λ₀ code and these weights are released under Apache 2.0. The [Qwen3.5-2B base model](https://huggingface.co/Qwen/Qwen3.5-2B) is also available under Apache 2.0.
+The λ₀ code and these weights are released under Apache 2.0. The [Qwen3.5-2B base model](https://huggingface.co/Qwen/Qwen3.5-2B) is also available under Apache 2.0.