Article
Asynchronous Robot Inference: Decoupling Action Prediction and Execution
- +5
•
45
Dana Aubakirova
danaaubakirova
AI & ML interests
DocumentAI, Deep Learning, Multimodal Learning, Computer Vision, Image Processing, NLP
Recent Activity
upvoted
an
article
12 days ago
huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning
updated
a dataset
24 days ago
HuggingFaceVLA/community_dataset_v2
updated
a dataset
24 days ago
HuggingFaceVLA/community_dataset_v1
Organizations
published
an
article
5 months ago
published
an
article
6 months ago
Article
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
-
- +7
•
289
published
an
article
7 months ago
Article
LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?
-
- +5
•
86
published
an
article
8 months ago
Article
Porting Pi0-FAST to LeRobot from JAX to PyTorch: Challenges, Fixes, and Open Questions
•
14
published
an
article
10 months ago
Article
π0 and π0-FAST: Vision-Language-Action Models for General Robot Control
-
- +2
•
184
published
an
article
over 1 year ago
Article
Introducing TextImage Augmentation for Document Images
-
-
- +1
•
33
published
an
article
over 1 year ago
Article
LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?
•
17
published
an
article
over 1 year ago
Article
Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task
•
17