Cerberus: Open SSM-Based Genomic Models Beat Transformers on QTL Prediction
anshulkundaje · x · 2026-10-10
A team released a preprint exploring state space models (SSMs) for long-sequence genomic prediction, alongside Cerberus, an open set of PyTorch models built on this work. Swapping transformers for SSMs yields better QTL predictions and faster sequence mixing. State-space duality also makes the models interpretable: shallow layers stay local while deeper layers reach farther and anchor on TSSs and CTCF sites. Preprint and code are open.
Related event: Cerberus: open-source SSM models for long-sequence genomic prediction(2 posts)→
More from Research
- Salesforce's Opera critic framework boosts coding agent resolve rates by up to 15 points — Salesforce · 2026-10-10
- visloc-rs: pure-Rust visual-inertial SLAM, SfM and 3D Gaussian Splatting toolkit — rsasaki0109 · 2026-10-10
- Agent Arena swaps preference voting for causal tracing to benchmark agents — arena · 2026-10-10
- WOVEN: visual transition reasoning as a shared primitive lifts 22 of 26 benchmarks by up to 27.3 points — mohitban47 · 2026-10-10
- OpenAI Open-Sources Internal Model's Math Results: Proofs, Lean Artifacts and Reasoning Traces — keunwoochoi · 2026-10-10
- Mathematicians debate how AI-generated proofs should reshape the seminar talk — LucaAmb · 2026-10-10