# Electroencephalography

In cross-subject neural-image retrieval, comparing the mean of a few target observations with the global source mean conflates subject-specific representation shifts with differences in which stimuli were sampled. SA-LBC instead estimates a first-order shift by averaging residuals against same-stimulus source-population anchors, then shrinks the correction using source-derived uncertainty. On THINGS-EEG2 with 10 subjects under leave-one-subject-out evaluation, the Attention-CLIP ViT-B/32 configuration rises from 0.1867 MRR without calibration to 0.2013 and 0.2336, though retrieval gains remain representation-dependent.

In cross-subject neural-image retrieval, comparing the mean of a few target observations with the global source mean conflates subject-specific representation shifts with differences in which stimuli were sampled. SA-LBC instead estimates a first-order shift by averaging residuals against same-stimulus source-population anchors, then shrinks the correction using source-derived uncertainty. On THINGS-EEG2 with 10 subjects under leave-one-subject-out evaluation, the Attention-CLIP ViT-B/32 configuration rises from 0.1867 MRR without calibration to 0.2013 and 0.2336, though retrieval gains remain representation-dependent.

Weight-space programming lets a language model read and edit a trained network's weights directly, and had been shown on game-playing networks and language models. Applied to EEG and ECG models, Claude Opus 5.5 wrote all 2,730 weights of TinyEEGNet with no gradient step and only five practice subjects, reaching 0.834 balanced accuracy on 65 unseen subjects, on par with 0.806 for the same architecture trained on 30 subjects and above 0.704 trained on five; it could not infer a network's task from its weights, nor improve an already well-trained network.

Weight-space programming lets a language model read and edit a trained network's weights directly, and had been shown on game-playing networks and language models. Applied to EEG and ECG models, Claude Opus 5.5 wrote all 2,730 weights of TinyEEGNet with no gradient step and only five practice subjects, reaching 0.834 balanced accuracy on 65 unseen subjects, on par with 0.806 for the same architecture trained on 30 subjects and above 0.704 trained on five; it could not infer a network's task from its weights, nor improve an already well-trained network.

Sleep foundation models compress multi-second EEG into compact tokens, leaving too little temporal detail to trace the onset and offset of sleep spindles. One approach keeps the SleepFM encoder frozen and adds a local time-frequency branch that preserves 11–16 Hz sigma-band energy and intra-token position, then uses residual cross-attention to bring in pretrained temporal context. On the MODA benchmark across six folds, event-level F1 is 0.8080±0.0040 at IoU 0.2 and 0.7766±0.0050 at IoU 0.5, with a faster decline at stricter boundary overlap.

Sleep foundation models compress multi-second EEG into compact tokens, leaving too little temporal detail to trace the onset and offset of sleep spindles. One approach keeps the SleepFM encoder frozen and adds a local time-frequency branch that preserves 11–16 Hz sigma-band energy and intra-token position, then uses residual cross-attention to bring in pretrained temporal context. On the MODA benchmark across six folds, event-level F1 is 0.8080±0.0040 at IoU 0.2 and 0.7766±0.0050 at IoU 0.5, with a faster decline at stricter boundary overlap.

Clinical EEG interpretation must cover technical quality, background and sleep states, interictal and ictal abnormalities across a whole recording, then synthesize a report, so event detection alone is not enough. ERIA has a locally deployed 27B language-model controller call deterministic signal analyses, learned clinical models and local knowledge retrieval, while controller weights, tools and safety constraints stay fixed and only the natural-language analysis policy is rewritten by GEPA using feedback from expert reports. On 200 paired clinical EEGs, the physician-aligned report score on the protected test set rose from 0.5052 to 0.6024, and the policy still performed on CerebraGloss-Bench and BrainBench Foundational Analysis.

Clinical EEG interpretation must cover technical quality, background and sleep states, interictal and ictal abnormalities across a whole recording, then synthesize a report, so event detection alone is not enough. ERIA has a locally deployed 27B language-model controller call deterministic signal analyses, learned clinical models and local knowledge retrieval, while controller weights, tools and safety constraints stay fixed and only the natural-language analysis policy is rewritten by GEPA using feedback from expert reports. On 200 paired clinical EEGs, the physician-aligned report score on the protected test set rose from 0.5052 to 0.6024, and the policy still performed on CerebraGloss-Bench and BrainBench Foundational Analysis.

EEG fatigue detection has treated multi-band modeling and temporal weighting as separate concerns, without defining how the spectral structure inside a window should shape that window's contribution. LBSNet encodes each window's relative cross-band activity as a normalized descriptor, softly matches it to learnable spectral prototypes, and combines the assignments with prototype importance to weight power aggregation. In subject-independent experiments on SEED-VIG and SADT it beats seven baselines on accuracy and F1 while using the fewest parameters and multiply-accumulate operations among the compared models.

EEG fatigue detection has treated multi-band modeling and temporal weighting as separate concerns, without defining how the spectral structure inside a window should shape that window's contribution. LBSNet encodes each window's relative cross-band activity as a normalized descriptor, softly matches it to learnable spectral prototypes, and combines the assignments with prototype importance to weight power aggregation. In subject-independent experiments on SEED-VIG and SADT it beats seven baselines on accuracy and F1 while using the fewest parameters and multiply-accumulate operations among the compared models.

A multi-scale biophysical model couples sleep homeostasis, circadian drive, a hypothalamic switch and a cortical spiking network to simulate five sleep disorders under one 72-hour photoperiod; paradoxical insomnia reaches the same total sleep time as controls yet scores lowest on restoration.

A multi-scale biophysical model couples sleep homeostasis, circadian drive, a hypothalamic switch and a cortical spiking network to simulate five sleep disorders under one 72-hour photoperiod; paradoxical insomnia reaches the same total sleep time as controls yet scores lowest on restoration.

CogAdapt derives program-level and token-level priors from human EEG and eye-tracking data recorded during code reading, combines them with a frozen MoE model's response to each coding task to dynamically select a small set of transformer blocks for sparse fine-tuning, and reports consistent correspondence between human reading behavior and MoE computation across Qwen and GLM, best pass@1 on LiveCodeBench and BigCodeBench, gains of 10.86 and 6.29 percentage points over matched regular all-block fine-tuning on LiveCodeBench, and an 86.21–87.21% reduction in gradient-eligible adaptation parameters.

CogAdapt derives program-level and token-level priors from human EEG and eye-tracking data recorded during code reading, combines them with a frozen MoE model's response to each coding task to dynamically select a small set of transformer blocks for sparse fine-tuning, and reports consistent correspondence between human reading behavior and MoE computation across Qwen and GLM, best pass@1 on LiveCodeBench and BigCodeBench, gains of 10.86 and 6.29 percentage points over matched regular all-block fine-tuning on LiveCodeBench, and an 86.21–87.21% reduction in gradient-eligible adaptation parameters.