Paper: “Flies are all you need” (on fly-language model)

Artificial Scientific · 1 month ago · 30 ● 4 sources

The Fly Language Model paper coupled a fixed MaleCNS connectome (as a reservoir) to a frozen 1.17-billion-parameter language backbone and trained only a 278,528-parameter readout. On 32 newly held-out conversations, negative log-likelihood dropped by 0.0222 nats per target token versus the frozen model, but a parameter-matched direct-input readout did slightly better (by +0.000488 nats per token for the fly model). The authors conclude the connectome measurably changes predictions yet does not outperform the simpler matched control, and they release conversational-training code while not releasing the archive or fitted readouts.