Researchers compile a larval fish brain into a simulated circuit running 26x faster than spiking models
mtizard · x · 2026-10-08
PRAGMA Research's "Fish in the Matrix" project compiles a measured larval zebrafish connectome into Cadence patch nets and runs the whole brain live in a browser, at 26x the efficiency of a spiking model.
- The wiring graph comes from measured connectome data, preserving connection partners and synapse counts, with declared neuron and body models added on top
- A gaze-circuit training demo lets you teach the fish to hold its gaze and return, with connection-strength changes kept between lessons via pause learning, and resettable at will
- A Platynereis larva model shows how light and touch drive its compiled sensory and motor pathways with fixed connections
Demo and source code are available online.
More from Embodied
- RLHND turns video diffusion models into physically grounded hand trackers for robot learning — RLWRLD · 2026-10-08
- NEEDLEwork stitches suboptimal robot demos into better training data — SongShuran · 2026-10-08
- Stanford's MobileVISTA fixes mobile manipulation's pose brittleness with generative data augmentation — jiajunwu_cs · 2026-10-08
- US Treasury issues first outbound investment fine: $200k over $92k Chinese robotics AI deal — pstAsiatech · 2026-10-08
- Palmer Luckey: I Believe in Humanoid Robots, But Won't Build Them Myself — PeterDiamandis · 2026-10-08
- Adding Motion Sense to VLAs With Frozen SAM 2 Lets Robots Catch Moving Bottles — nikhilaravi · 2026-10-08