AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models

Ganxi Xu, Zhao-Rong Lai, Yuting Tang, Yonghao Song, Guoxu Zhou, Boyu Wang, Jian Zhu, Jinyi Long

ICML 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 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
add CLIP text embeddings from LLM captions (ablation)DiT image-to-brain model · THINGS-EEG2MSE: 0.117 -> 0.109Improved
add CLIP text embeddings from LLM captions (ablation)DiT image-to-brain model · THINGS-MEGMSE: 0.677 -> 0.663Improved
add brain region embeddings (ablation)DiT image-to-brain model · THINGS-EEG2Pearson: 0.383 -> 0.425Improved
add brain region embeddings (ablation)DiT image-to-brain model · THINGS-MEGPearson: 0.337 -> 0.379Improved
add temporal embeddings (ablation)DiT image-to-brain model · THINGS-EEG2Pearson: 0.395 -> 0.425Improved
add temporal embeddings (ablation)DiT image-to-brain model · THINGS-MEGPearson: 0.349 -> 0.379Improved
use Qwen2-VL-2B instead of VisualGLM for captions (ablation)DiT image-to-brain model · THINGS-EEG2MSE: 0.147 -> 0.109Improved
use Qwen2-VL-2B instead of MiniGPT-4 for captions (ablation)DiT image-to-brain model · THINGS-MEGMSE: 0.689 -> 0.663Improved
keep occipital channels (vs removing them) (ablation)DiT image-to-brain model · THINGS-EEG2MSE: 0.200 -> 0.109Improved
keep occipital channels (vs removing them) (ablation)DiT image-to-brain model · THINGS-MEGPearson: 0.295 -> 0.379Improved
use DiT with cross-attention instead of SynBrainimage-to-brain generation · THINGS-EEG2Pearson: 0.366 -> 0.425Improved
test on different subjects than training (cross-subject)Our work · THINGS-MEGPearson: 0.379 -> 0.082Hurt

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