Fly Language Model (FLM) Wires the Full Fruit Fly Connectome Into a Frozen 1.2B LLM, and Its Own Controls Show the Wiring Does Not Help
Researchers wire the full fruit fly connectome (166,700 nodes) into a frozen LiquidAI LFM2.5-1.2B LLM, but controls show no fly-specific benefit.
The Fly Language Model (FLM) couples the complete MaleCNS v1.0 fruit fly connectome (166,700 nodes, 25,582,938 edges) to a frozen LiquidAI LFM2.5-1.2B-Instruct backbone, training only a 278,528-parameter readout (~0.0238% of backbone parameters). The fly readout improved NLL by 0.0222 nats/token (perplexity 3.98 to 3.90) on 32 SmolTalk dialogues, but a direct-input control without the graph beat it in all three seeds. Relabeling node identities removes the gain and the recurrence contracts state differences by 0.6 per token, so the connectome adds no long-range memory. The MIT-licensed code runs locally on Python 3.12, but study artifacts remain private, limiting independent reproducibility.
- Full MaleCNS v1.0 fly connectome (166,700 nodes, 25.6M edges) drives a frozen LiquidAI LFM2.5-1.2B backbone.
- Only 278,528 readout parameters train; fly readout cuts NLL 0.0222 nats/token (perplexity 3.98 to 3.90).
- A no-graph direct-input control beats the fly readout in all seeds; bootstrap interval shows no fly-specific gain.
- Relabeling node identities breaks the gain, indicating interface alignment rather than fly topology matters.
- MIT-licensed code runs locally, but private study artifacts limit independent verification.
From the original article
3 min read at marktechpost.com
The Fly Language Model (FLM) drives all 166,700 retained neurons and 25. 6 million edges of the MaleCNS fruit fly connectome with token embeddings, then adds a small learned correction to a frozen LFM2. 5-1.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.