VQV Signal

ROBOTS & HARDWARE WATCH TECHNICAL

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...

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-14T05:45:00+00:00 Detected 2026-11-14T14:22:11+00:00
View original source

@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.

Signal Strength 88% Technical label WATCH Public Interest 36 Category ROBOTS & HARDWARE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 0 Practical Impact Score 8 Novelty Interest Score 70 Consequence Score 50 Curiosity Score 84 Shareability Score 42

VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).