Update README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: mit
 library_name: pytorch
 tags:
 - robotics
@@ -31,31 +30,13 @@ This model is trained for robotic manipulation tasks using vision-language-actio
 - **Dataset**: LIBERO-10 (29 subtasks, 1,354 demonstrations)
 - **Segmentation**: Semantic action chunking using Gemini Vision API
 - **Framework**: PyTorch
-- **Checkpoint**: Epoch 90
-
-## Usage
-
-```python
-import torch
-from pathlib import Path
-
-# Load checkpoint
-checkpoint = torch.load(
-    "checkpoints/libero_10_fixed_training_v1/epoch_90.pt",
-    map_location="cuda"
-)
-
-# Extract model state
-model_state = checkpoint['model_state_dict']
-
-# TODO: Add inference code here
-```
+- **Checkpoint**: Epoch 90 (best_epoch)
 
 ## Performance
 
 Training run: `libero_10_fixed_training_v1`
 
-*Add your metrics here after evaluation*
+*Overall performance accuracy: 88.8 % task success rate => 5 % better than raw CLIP-RT on LIBERO-LONG*
 
 ## Dataset
 
@@ -67,11 +48,12 @@ This model was trained on the [GATE-VLAP Datasets](https://huggingface.co/datase
 ## Citation
 
 ```bibtex
-@article{gateVLAP2024,
-  title={GATE-VLAP: Grounded Action Trajectory Embeddings with Vision-Language Action Planning},
-  author={[Your Name]},
+@article{gateVLAP@SAC2026,
+  title={Atomic Action Slicing: Planner-Aligned Options for Generalist VLA Agents},
+  author={Stefan Tabakov, Asen Popov, Dimitar Dimitrov, Ensiye Kiyamousavi and Boris Kraychev},
   journal={arXiv preprint arXiv:XXXX.XXXXX},
-  year={2024}
+  conference={The 41st ACM/SIGAPP Symposium On Applied Computing (SAC2026), track on Intelligent Robotics and Multi-Agent Systems (IRMAS)},
+  year={2025}
 }
 ```
 
@@ -83,8 +65,5 @@ This model was trained on the [GATE-VLAP Datasets](https://huggingface.co/datase
 
 - 🤗 **Dataset**: [gate-institute/GATE-VLAP-datasets](https://huggingface.co/datasets/gate-institute/GATE-VLAP-datasets)
 - 📄 **Paper**: *Coming soon*
-- 💻 **Code**: *Add your GitHub repo here*
-
-## License
+- 💻 **Code**: *Coming soon*
 
-MIT License