m1b/parameter-golf-novel
Updated
Marina Barannikov
m1b
AI & ML interests
None yet
Recent Activity
updated a model about 9 hours ago
m1b/parameter-golf-novel published a model about 11 hours ago
m1b/parameter-golf-novel updated a Space about 12 hours ago
m1b/sandbox-57441308Organizations
updated a
model about 9 hours ago
published a
model about 11 hours ago
updated a
Space about 12 hours ago
liked a
dataset about 2 months ago
authored a
paper 2 months ago
upvoted a paper 2 months ago
upvoted 2
articles 5 months ago
Article
LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?
- +5
•
96
Article
Is using a validation set useful for end-to-end learning in robotics?
•
11
liked 2
datasets 9 months ago
upvoted a paper 10 months ago
liked a
model 10 months ago
reacted to m-ric's post with 🔥 11 months ago
Post
1782
If you didn't yet, you should read the technical report for SmolVLA, published yesterday by the Hugging Face robotics team!
➡️ Amongst other ideas, it introduces "Async inference" to boost their robot actions.
Robots have a problem: performing the actions takes time (Unlike agents where action executions are near-instant!)
Most often, robots wait until they've finished performing actions to start thinking about hte next steps. This is a huge latency cost!
So the team decided to have the PolicyServer (aka the"thinking" part) restart early : instead of waiting for the n observations they just sent to be completed, they gather the observations after k < n steps, and start preparing the next actions based on that while the steps are running until n, to directly send their next steps.
➡️ This boosted robot throughput by ~30%! (nearly 2× tasks per time window).
gg @cadene and team! 👏
Report here: SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics (2506.01844)
➡️ Amongst other ideas, it introduces "Async inference" to boost their robot actions.
Robots have a problem: performing the actions takes time (Unlike agents where action executions are near-instant!)
Most often, robots wait until they've finished performing actions to start thinking about hte next steps. This is a huge latency cost!
So the team decided to have the PolicyServer (aka the"thinking" part) restart early : instead of waiting for the n observations they just sent to be completed, they gather the observations after k < n steps, and start preparing the next actions based on that while the steps are running until n, to directly send their next steps.
➡️ This boosted robot throughput by ~30%! (nearly 2× tasks per time window).
gg @cadene and team! 👏
Report here: SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics (2506.01844)
upvoted a paper 11 months ago
published an article 12 months ago
Article
LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?
- +5
•
96
upvoted an article about 1 year ago
Article
🏆 Mistral AI Robotic Hackathon – 2nd Place: “LeCopain” 🤖
•
9
updated a
model about 1 year ago
published a
model about 1 year ago
updated a
dataset about 1 year ago
published a
dataset about 1 year ago