Yi Ding

Unsupervised EEG domain adaptation is unlocked by treating distribution shifts as linear transformations on the SPD manifold, enabling interpretable alignment without labeled calibration data.

Unlabeled physiological signals unlock multimodal EEG foundation model adaptation, matching supervised performance with zero-shot generation.

Autonomous LLM agents guided by early learning-curve forecasting can discover generalist EEG architectures that outperform state-of-the-art foundation models across 14 diverse clinical and affective benchmarks.

Minimizing energy consumption in LLM inference does not ensure ecological sustainability: spatial and temporal deployment choices cause stark divergence across carbon, water, and biodiversity impacts that can double worst-case environmental regret.

It is tested whether models in this deployment-relevant 2--8B range carry genuine taxonomic knowledge, evaluating four such VLMs against the domain-specific specialist BioCLIP on a 96-species task, and comparing clean iNaturalist photographs against camera-trap imagery from 6 LILA.

OPD's effectiveness hinges less on teacher supervision than previously thought, with a new method achieving a staggering 263% relative gain without any teacher input.

Counterfactual arithmetic in latent models primarily travels through value-cache suffixes, challenging assumptions about hidden states and keys.