BATv1: 46k-Parameter Genomics Models Beat 114k-Parameter BPNet on Accuracy
jmschreiber91 · x · 2026-10-31
New BATv1 transcription factor binding models are remarkably small — only 46k parameters vs 614k for CATv1 accessibility models and 114k for BPNet models — yet very accurate. The author reports BATv1 usually provides a modest improvement over BPNet, with formal comparisons coming in a preprint. Coverage charts show models spanning major TF families including C2H2 ZF, Homeodomain and bHLH. A notable small-model-beats-big-model case for AI in genomics.
More from Research
- NVIDIA Nemotron 3.5 scales LLM self-verification, +9-10 points on agentic benchmarks — sarahcat21 · 2026-10-31
- Unofficial OpenTargets MCP Server Brings Gene-Drug-Disease Data to LLMs — modelcontextprotocol · 2026-10-31
- Researchers find 5 personality structures in LLM weight space, Big Five-like — luke_drago_ · 2026-10-31
- NVS benchmarks are misaligned: proper pose alignment puts 3D Gaussians back at SOTA — kwangmoo_yi · 2026-10-31
- arXiv moderator: submission surge causes months-long holds, new moderators wanted — tdietterich · 2026-10-31
- arXiv policy checks reject class projects, proposals, surveys and position papers — tdietterich · 2026-10-31