@jmtang42 and Song Han's team say they trained an open 27B model built on Qwen3.8-27B to control robots purely from its own attempts in simulation, with zero demonstrations. They report it went from 0 to 18 of 30 tests on a real robot it had never tou...
VQV Signal
PEAR: an open 27B model learns to drive real robot arms from simulation alone
@jmtang42 and Song Han's team say they trained an open 27B model built on Qwen3.8-27B to control robots purely from its own attempts in simulation, with zero demonstrations. They report it went from 0 to 18 of 30 tests on a real robot it had never tou...
@jmtang42 and Song Han's team say they trained an open 27B model built on Qwen3.8-27B to control robots purely from its own attempts in simulation, with zero demonstrations. They report it went from 0 to 18 of 30 tests on a real robot it had never touched, runs locally at over 220 tokens a second on an RTX 5090,...
Hardware and robotics watchers may want to track whether this becomes a product, benchmark, or deployment signal.
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.