AI Paper Atlas

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

AVM: Towards Structure-Preserving Neural Response Modeling in the Visual Cortex Across Stimuli and Individuals

Qi Xu, Shuai Gong, Xuming Ran, Haihua Luo, Yangfan Hu

AAAI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: fMRI visual decoding · 0 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
replace full fine-tuning (V1T-T) with frozen backbone plus modulation paths (AVM)V1T · Dataset F (adapted from Dataset S)FEVE: 0.6662 -> 0.7536Improved
replace training from scratch (V1T-D) with AVM adaptationV1T · Dataset F (adapted from Dataset S)FEVE: 0.6363 -> 0.7536Improved
use frozen backbone with modulation instead of full tuningV1T · trainable parametersparameter count: 2.46M -> 0.11MImproved
use block-specific modulation instead of one shared path (AVM vs AVM-S)AVM-S · Dataset F (adapted from Dataset S)FEVE: 0.7515 -> 0.7536No clear effect
add cross-block Cross-CAMU (AVM-B vs AVM)AVM · Dataset F (adapted from Dataset S)FEVE: 0.7536 -> 0.7467Hurt
raise modulation weight from 0.1 to 1.0 (ablation)AVM · Dataset F (adapted from Dataset S)FEVE: 0.5507 -> 0.7536Improved
raise modulation weight from 1.0 to 2.0 (ablation)AVM · Dataset F (adapted from Dataset S)FEVE: 0.7536 -> 0.6824Hurt
raise modulation weight from 1.0 to 2.0 (ablation)AVM · Dataset S (adapted)FEVE: 0.6054 -> 0.6094Improved
increase bottleneck dimension from 1 to 31 (ablation)AVM · Dataset F (adapted from Dataset S)FEVE: 0.7219 -> 0.7536Improved
increase bottleneck dimension from 1 to 100 (ablation)AVM · Dataset S (adapted)FEVE: 0.5589 -> 0.6225Improved
add subject-specific conditioning (AVM vs AVM-S)AVM-S · Dataset S (mouse C)FEVE: 0.8271 -> 0.8424Improved

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