BestHub
Sign in
HyperAI Super Neural
HyperAI Super Neural
Apr 20, 2026 · Artificial Intelligence

dnaHNet Boosts Inference Speed 3× and Cuts Genomic Learning Cost by Nearly 4×

The dnaHNet model, introduced by researchers from the University of Toronto, Vector AI Institute, and Arc Institute, achieves over three‑fold faster inference and nearly four‑fold lower computational cost than prior genomic foundation models, while delivering state‑of‑the‑art zero‑shot performance on variant effect prediction, gene essentiality classification, and unsupervised reconstruction of functional genome architecture.

Computational EfficiencydnaHNetdynamic tokenization
0 likes · 11 min read
dnaHNet Boosts Inference Speed 3× and Cuts Genomic Learning Cost by Nearly 4×
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Sep 23, 2025 · Artificial Intelligence

One-Embedding-Fits-All: Selecting the Best Time-Series Forecasting Model from a Model Zoo

The paper introduces ZooCast, a framework that builds a model zoo of time‑series foundation models and uses a One‑Embedding‑Fits‑All paradigm to embed models and tasks into a unified space, enabling efficient zero‑shot selection that outperforms single models and full‑model ensembles on the GIFT‑Eval benchmark while remaining computationally lightweight.

GIFT-EvalOne-Embedding-Fits-AllTSFM
0 likes · 10 min read
One-Embedding-Fits-All: Selecting the Best Time-Series Forecasting Model from a Model Zoo