TinyAstral: distilling a 180B teacher into 0.8-4B agents for edge robotics
ResearchSource:Hugging Face (paper)
The paper evolves the harness of a ~180B robot teacher — from 33.4% to 63.6% on RoboTwin — and distills the result into 0.8-4B students running at a fifth of the compute, including closed loop on a real arm. Code, weights and data released.
Related articles
Cosmos 3 Edge: the DROID policy for robotics that runs on the edge
Cosmos3-Edge-Policy-DROID: NVIDIA's 4B robotic policy. How much hardware you need to run it in real time on a Jetson, and where it stops.
ML agents that run locally: MLExpert and EpochGo on Ollama, zero API costs
MLExpert raises the bar to 35B and a 72.7% medal rate; EpochGo runs three AutoML agents on 16 GB at zero API cost: what works today, the math and the limits.
Local text-to-SQL: query your business database without sending data to the cloud
A local model, the schema to the model, execution on your database: text-to-SQL in-house, ARCS benchmark numbers, and where it really breaks.
Get the next local-AI briefing
Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.
After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.