AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Exploring The Visual Feature Space for Multimodal Neural Decoding

Weihao Xia, Cengiz Oztireli

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 3 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
add masked denoising loss to feature regression for brain alignment (ablation)VINDEX · MG-BrainDUB descriptive captioningCAPTURE: 0.4179 -> 0.4356Improved
make denoiser deeper (3 layers) or weight denoising loss at 2.0 (ablation)VINDEX denoiser · MG-BrainDUB descriptive captioningCAPTURE: 0.4356 -> 0.4096Hurt
align brain with 9-token nested CLIP features instead of single-encoder full features (ablation)VINDEX · MG-BrainDUB descriptive captioningCAPTURE: 0.4356 -> 0.5021Improved
nested feature with 144 tokens instead of 9 (ablation)VINDEX · MG-BrainDUB descriptive captioningCAPTURE: 0.5021 -> 0.1614Hurt
aggregate multi-layer SigLIP features (AF) as alignment target (ablation)VINDEX · MG-BrainDUB descriptive captioningCAPTURE: 0.4356 -> 0.0058Hurt
mix CLIP and DINO features (mixture of encoders) (ablation)VINDEX · MG-BrainDUB descriptive captioningCAPTURE: 0.4733 -> 0.3041 (SE vs ME, LLaVA-1.5 13B)Hurt
use CLIP-336 instead of CLIP-224 target features (ablation)VINDEX · MG-BrainDUB descriptive captioningCAPTURE: 0.4877 -> 0.4120 (NF1)Hurt
scale MLLM from LLaVA-1.5 7B to LLaVA-1.6 or 13B with single-encoder features (ablation)VINDEX SE · MG-BrainDUB descriptive captioningCAPTURE: 0.4356 -> 0.4733 (1.5 13B), 0.4684 (1.6 7B)Mixed
use VINDEX instead of UMBRAE for brain groundingVINDEX · BrainHub concept localization (All)acc@0.5: 18.03 -> 18.10No clear effect
decode location directly from brain signals instead of from reconstructed imagesVINDEX · BrainHub concept localization (All)acc@0.5: 15.34 -> 18.10Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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