flâneur

π0.5 on the edge at 43 Hz — Guild

guildrobotics.com · 914 words · saved by 1 readers

Building robotics for the commerce age.

We attack inference latency from several fronts. Specifically, we combine Shallow-π [1] and SnapFlow distillation [2] with TensorRT compilation and quantization [3]. Throughout we evaluate on two simulated setups: LIBERO [5]: a widely used benchmark with 40 tasks covering spatial, object, goal, as well as longer horizon entangled objectives RoboLab [6]: a new photorealistic benchmark intended to address generalization and saturation in existing frameworks Step 1: Shallow-π First, we adopt the knowledge distillation technique Shallow-π [1]. π0.5 is composed of a 2.6 billion parameter…

saved by

related reading