Karl Pertsch

KarlP's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in physical-intelligence/fast 8 days ago

Decode ground truth token but get 25% success rate on libero-10

3

#15 opened 8 days ago by

Felix-Zhenghao

New activity in physical-intelligence/fast 10 days ago

FAST+ uses relative or absolute actions ?

3

#13 opened 10 days ago by

BrunoM42

New activity in physical-intelligence/fast 11 days ago

One second of action decoded to >500 tokens

1

#12 opened 11 days ago by

WonderYear1905

New activity in physical-intelligence/fast 25 days ago

Action Decoding Errors

6

#4 opened about 2 months ago by

kiddyna

updated a dataset about 1 month ago

physical-intelligence/libero

Viewer • Updated Feb 2 • 273k • 6.15k • 4

published a dataset about 1 month ago

physical-intelligence/libero

Viewer • Updated Feb 2 • 273k • 6.15k • 4

New activity in physical-intelligence/fast about 2 months ago

Trained on custom dataset not working

5

#5 opened about 2 months ago by

andvg3

updated a model about 2 months ago

KarlP/fast-droid

Updated Jan 21 • 1

published a model about 2 months ago

KarlP/fast-droid

Updated Jan 21 • 1

authored a paper about 2 months ago

FAST: Efficient Action Tokenization for Vision-Language-Action Models

Paper • 2501.09747 • Published Jan 16 • 23

updated a model about 2 months ago

physical-intelligence/fast

Robotics • Updated Jan 16 • 86

published a model about 2 months ago

physical-intelligence/fast

Robotics • Updated Jan 16 • 86

updated a model 3 months ago

KarlP/droid

Updated Dec 21, 2024

authored a paper 9 months ago

OpenVLA: An Open-Source Vision-Language-Action Model

Paper • 2406.09246 • Published Jun 13, 2024 • 37

authored a paper 10 months ago

Octo: An Open-Source Generalist Robot Policy

Paper • 2405.12213 • Published May 20, 2024 • 28