Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# LeHome Challenge 2026 — Submission
|
| 2 |
|
| 3 |
**Method**: SmolVLA (frozen four_types 30K backbone) + state-only residual MLP, trained with sparse-reward residual RL on 40 Seen garments. Single model, deterministic inference.
|
|
@@ -149,3 +163,5 @@ Inference is fully deterministic. Two runs with the same backbone, residual chec
|
|
| 149 |
## Contact
|
| 150 |
|
| 151 |
vita / realvitacai@gmail.com
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- lehome/dataset_challenge
|
| 4 |
+
- lehome/dataset_challenge_merged
|
| 5 |
+
base_model:
|
| 6 |
+
- HuggingFaceTB/SmolVLM2-500M-Video-Instruct
|
| 7 |
+
pipeline_tag: robotics
|
| 8 |
+
tags:
|
| 9 |
+
- robotics
|
| 10 |
+
- lerobot
|
| 11 |
+
- lehome-challenge
|
| 12 |
+
- smolvla
|
| 13 |
+
- residual-rl
|
| 14 |
+
---
|
| 15 |
# LeHome Challenge 2026 — Submission
|
| 16 |
|
| 17 |
**Method**: SmolVLA (frozen four_types 30K backbone) + state-only residual MLP, trained with sparse-reward residual RL on 40 Seen garments. Single model, deterministic inference.
|
|
|
|
| 163 |
## Contact
|
| 164 |
|
| 165 |
vita / realvitacai@gmail.com
|
| 166 |
+
|
| 167 |
+
klein / kleinlau17@gmail.com
|