Research map / Vision-language and multimodal / Human and embodied modeling
BrainLMM: A Label-Free Framework for Mapping Multi-Semantic Representation in the Human Visual Cortex
Tan Gao, Mufan Xue, Haofang Zheng, Shuo Lv, Jia Xu, Dabin Sheng, Ziming Mao, Xinyu Wu, Andrew Luo, Guoyuan Yang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use BrainLMM instead of CLIP-MSM for voxel semantic labels | CLIP-based voxel encoding models (NSD S5) · NSD S5 selective ROIs (EBA, RSC, FOOD, VWFA) | cosine similarity between label text embedding and voxel weights | Improved |
| use BrainLMM instead of CLIP-MSM in FFA | CLIP-based voxel encoding models (NSD S5) · NSD S5 FFA | cosine similarity between label text embedding and voxel weights | No clear effect |
| use BrainLMM instead of CLIP-MSM with ResNet50-CLIP backbone | ResNet50 CLIP encoder · NSD S5 faces, bodies, places, food, words | Pearson correlation with ground-truth voxel responses | Improved |
| use BrainLMM instead of CLIP-MSM with ViT-B/32 CLIP backbone | ViT-B/32 CLIP encoder · NSD S5 places, food, bodies, words | Pearson correlation with ground-truth voxel responses | Improved |
Closest papers by meaning
- CLIP-MSM: A Multi-Semantic Mapping Brain Representation for Human High-Level Visual Cortex (AAAI 2025 · similarity 0.93)
- Finding Shared Decodable Concepts and their Negations in the Brain (ICLR 2025 · similarity 0.90)
- Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformers (ICLR 2025 · similarity 0.89)
- BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity (ICLR 2024 · similarity 0.89)
- In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain (NeurIPS 2025 · similarity 0.89)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.89)
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.
