Subject identity variance dominates frozen representations in three EEG foundation models by 13-89x over null, and erasing the linear subject axis improves label decoding where within-subject label variation exists.
AdaBrain-Bench : Benchmarking brain foundation models for brain-computer interface applications
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.LG 5years
2026 5representative citing papers
OmniEEG-Bench unifies 54 EEG datasets into six task families and benchmarks 10 foundation models, finding that pretraining diversity and model size correlate with better average performance ranks.
NeuroAtlas benchmarks foundation models on 42 EEG datasets and reports that EEG-specific models do not consistently outperform generic time-series models, standard metrics miss clinical utility, and rankings vary by domain.
NeuralBench is a new benchmarking framework for neuroAI models on EEG data that finds foundation models only marginally outperform task-specific ones while many tasks like cognitive decoding stay highly challenging.
DLink distills layer-wise knowledge from EEG foundation models via a lightweight router and spectral alignment to produce compact students that narrow the gap to full EFMs on four benchmarks while reducing parameters, FLOPs, and inference latency.
citing papers explorer
-
The Identity Trap in EEG Foundation Models: A Diagnostic Audit
Subject identity variance dominates frozen representations in three EEG foundation models by 13-89x over null, and erasing the linear subject axis improves label decoding where within-subject label variation exists.
-
OmniEEG-Bench: A Standardized Evaluation Benchmark for EEG Foundation Models
OmniEEG-Bench unifies 54 EEG datasets into six task families and benchmarks 10 foundation models, finding that pretraining diversity and model size correlate with better average performance ranks.
-
NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
NeuroAtlas benchmarks foundation models on 42 EEG datasets and reports that EEG-specific models do not consistently outperform generic time-series models, standard metrics miss clinical utility, and rankings vary by domain.
-
NeuralBench: A Unifying Framework to Benchmark NeuroAI Models
NeuralBench is a new benchmarking framework for neuroAI models on EEG data that finds foundation models only marginally outperform task-specific ones while many tasks like cognitive decoding stay highly challenging.
-
DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models
DLink distills layer-wise knowledge from EEG foundation models via a lightweight router and spectral alignment to produce compact students that narrow the gap to full EFMs on four benchmarks while reducing parameters, FLOPs, and inference latency.