AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens

Konstantin Friedrich Willeke, Polina Turishcheva, Alex Gilbert, Goirik Chakrabarty, Hasan Atakan Bedel, Paul G. Fahey, Yongrong Qiu, Marissa A. Weis, Michaela Vystrčilová, Taliah Muhammad, Lydia Ntanavara, Rachel E Froebe and 9 more

ICLR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
scale model from 80M to 300M parameters (ablation)OmniMouse · 323 sessions forecastingsingle-trial correlation: 0.25 -> 0.25No clear effect
scale model from 80M to 300M parameters (ablation)OmniMouse · 323 sessions behavior decoding averagesingle-trial correlation: 0.77 -> 0.76No clear effect
scale model from 1M to 80M parameters (ablation)OmniMouse · 323 sessions forecastingsingle-trial correlation: 0.18 -> 0.25Improved
scale model from 1M to 80M parameters (ablation)OmniMouse · 323 sessions behavior decoding averagesingle-trial correlation: 0.68 -> 0.77Improved
scale training data from 8 to 323 sessions (5M model) (ablation)OmniMouse-5M · forecastingsingle-trial correlation: 0.18 -> 0.22Improved
scale training data from 8 to 323 sessions (5M model) (ablation)OmniMouse-5M · forecasting+stimulussingle-trial correlation: 0.25 -> 0.32Improved
scale training data from 8 to 323 sessions (5M model) (ablation)OmniMouse-5M · population+stimulussingle-trial correlation: 0.27 -> 0.35Improved
scale training data from 8 to 323 sessions (5M model) (ablation)OmniMouse-5M · behavior decoding averagesingle-trial correlation: 0.59 -> 0.69Improved
add visual stimulus input to forecasting (80M) (ablation)OmniMouse-80M · 323 sessions forecastingsingle-trial correlation: 0.25 -> 0.34Improved
train on 323 sessions instead of 8 sessions, versus baselines (ablation)OmniMouse · running speed decodingsingle-trial correlation: 0.44 -> 0.55Mixed
use OmniMouse over MtM baseline (data-matched)OmniMouse-5M · 8 sessions forecastingsingle-trial correlation: 0.12 -> 0.18Improved
use OmniMouse over Latent Model (data-matched)OmniMouse-5M · 8 sessions forecasting+stimulussingle-trial correlation: 0.18 -> 0.25Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy