Blog
Technical writing and release announcements from the CAIRN Institute.
Darwin
From FASTA to Regulatory Hypothesis — August 25, 2026
A new external sequence-to-network prototype benchmarked across 501 atlas-backed edges, showing strong gains from layered target-mapping and regulator-ranking evidence.
Darwin Validation Update — August 24, 2026
New data, biological benchmarking, and LLM stress testing across 8 species, 100 research skills, and deterministic + agent-driven validation.
Darwin Release Update — August 2026
100 research skills across 7 categories, LLM agent validation with GPT-5.4 and Nemotron-3-Ultra, and new workflow capabilities.
Darwin Initial Release — June 2026
Public release of Darwin for multi-species gene regulatory network research.
Project DoLittle
Hybrid LLM Architectures for Long-Context Whale Audio
How Hybrid SWA MoE and DeepSeek-style Hybrid NSA MoE architectures extend audio context while preserving a causal transformer decoder.
Public Release of Trained Neural Audio Models
Three trained DAC 9-codebook checkpoints for humpback whale communication — 10K, 32K, and 128K models for inference and fine-tuning.
Public Dataset Release: 10B Tokens of Humpback Whale Song
10 billion tokens of humpback whale song from NOAA SanctSound recordings, tokenized with 9-codebook DAC for long-context audio research.
MMC Humpback DAC9 Model Release Details
Technical details for the released humpback whale DAC9 model checkpoints.