functional magnetic resonance imaging
PulseAugur coverage of functional magnetic resonance imaging — every cluster mentioning functional magnetic resonance imaging across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
New technique maps AI model "thoughts" using neuroscience principles
Researchers have developed a novel method to probe the internal workings of large language models, drawing inspiration from neuroscience techniques. This approach, termed 'activation analysis,' uses functional magnetic …
-
New Transformer Framework Enhances Brain State Decoding with fMRI and Metadata
Researchers have developed a new framework that integrates transformer-based architectures with functional magnetic resonance imaging (fMRI) data and Digital Imaging and Communications in Medicine (DICOM) metadata for i…
-
LLMs Show Brain Alignment During Creative Thinking
A new study published on arXiv explores the alignment between large language models (LLMs) and the human brain during creative thinking tasks. Researchers used functional magnetic resonance imaging (fMRI) data from part…
-
Paramount film commitments, Chinese rocket failure, dog emotion research, and game remaster clarification
Paramount is reportedly committing to releasing 30 films annually for three years if its acquisition of Warner Bros. goes through, according to Deadline. In unrelated news, a Chinese rocket utilizing the YF-100 engine e…
-
New federated learning framework improves brain connectivity analysis across sites
Researchers have developed FedDOSE, a novel federated learning framework designed to improve the analysis of dynamic functional connectivity in brain imaging data across multiple sites. This framework addresses the chal…
-
New MPP-GNN model advances Alzheimer's classification using fMRI data
Researchers have developed a new graph neural network model called MPP-GNN for analyzing functional magnetic resonance imaging (fMRI) data to classify Alzheimer's disease. This model addresses limitations in existing me…
-
New fMRI2Face framework reconstructs faces from brain activity
Researchers have introduced fMRI2Face, a novel framework designed to reconstruct dynamic human faces from functional magnetic resonance imaging (fMRI) data. This framework is built upon the fMRI-Face dataset, the first …
-
New ST-VTD framework improves spatiotemporal data analysis for neuroimaging
Researchers have developed a new framework called Spatiotemporal Variational Tensor Decomposition (ST-VTD) to better model complex, subject-specific patterns in multisubject spatiotemporal data, particularly in neuroima…
-
AI models' brain alignment linked to meaning abstraction, not prediction
A new research paper suggests that the alignment between language and speech models and human brain responses stems from shared meaning abstraction rather than next-word prediction capabilities. The study found that int…
-
New deep learning models decode visual perception from brain activity
Researchers have developed new deep learning approaches for decoding visual semantic information from brain activity. One study utilizes an end-to-end Transformer-based deep learning framework with electrocorticography …
-
New KReTTaH framework offers data-free imputation via tensor trains
A new framework called KReTTaH has been introduced for multi-way data imputation, utilizing kernel regression with tensor trains and Hadamard overparameterization. This method is designed to be training-data-free, inter…
-
New metric shows semantic relevance tracks brain activity during speech comprehension
Researchers have developed a new metric called contextual semantic relevance to better understand brain activity during naturalistic speech comprehension. This metric, which measures how strongly an incoming word relate…
-
LLM linguistic competence drives left-right brain activity prediction asymmetry
Researchers have identified a left-right asymmetry in how large language models (LLMs) predict human brain activity, which emerges as the models develop formal linguistic competence. This asymmetry, observed using fMRI …
-
New fMRI decoding method shows language models obscure failures
Researchers have developed a new method for decoding continuous language from fMRI signals, improving upon existing encoding pipelines with expanded voxel selection and a more advanced language model. They also introduc…
-
New SpectralOT method aligns brain fMRI data across individuals
Researchers have developed a novel functional alignment method called SpectralOT for fMRI data. This technique aims to improve the generalization of brain activity decoders across individuals by aligning functional feat…
-
New BCI framework decodes multimodal brain signals using LLMs
Researchers have developed a novel framework for brain-computer interfaces (BCIs) that decodes language from brain signals by leveraging multimodal large language models (MLLMs). This approach aligns brain activity with…
-
Adversarial Robustness Improves CLIP-based Brain Decoding
Researchers have explored the use of CLIP, a vision-language model, for brain decoding tasks using fMRI data. They investigated whether adversarially robust representations could enhance neural decoding performance. By …
-
New RABBiT model predicts brain responses to speech with high accuracy
Researchers have developed RABBiT, a novel audio-to-fMRI encoder designed to predict brain responses to speech with high accuracy in zero-shot and few-shot scenarios. This model significantly outperforms existing state-…
-
Brain-inspired diffusion model reconstructs images from fMRI data
Researchers have developed Hi-DREAM, a novel brain-inspired hierarchical diffusion framework designed to improve the reconstruction of natural images from fMRI data. This method leverages the hierarchical organization o…
-
New AI Framework BrainPICM Enhances Brain Network Analysis
Researchers have developed BrainPICM, a novel self-supervised learning framework designed for brain network analysis. This method addresses the limitations of existing approaches by accounting for individual differences…