The paper introduces Sequential Contextual Fit (SCF), an embedding‑based metric that quantifies how well a current information state aligns with its recent context using a recency‑weighted similarity kernel. SCF is applied across diverse domains—including language, music, audiovisual emotion, gambling, activity recognition, and EEG—showing that lower contextual fit predicts longer processing times, larger affective or behavioural transitions, and stronger neural-state changes. These findings hold even after controlling for established predictors such as surprisal, prediction error, and sensory changes.
arXiv:2606. 05855v1 Announce Type: cross Abstract: Continuous electroencephalography (EEG) emotion prediction aims to model the temporal evolution of human emotional states from EEG signals.
Neural State Prediction (NSP) is a latent‑predictive framework designed to curb shortcut learning in EEG foundation models. By using a target encoder updated with an exponential moving average, identity residualization, and topology‑separated context, NSP constrains both the prediction target and the available context. Trained on 2.2 million EEG segments, NSP outperforms baselines on 14 datasets in the EEG‑FM‑Bench, achieving 63.94 % macro balanced accuracy.
NextMe-800 is an approximately 800‑hour first‑person video dataset collected from a single volunteer over 126 days, featuring 1 Hz images, gaze, and audio. The data are captioned at five hierarchical abstraction levels—from atomic actions to major activities—enabling personalized action anticipation as an open‑vocabulary K‑step sequence prediction task. The authors also introduce NextAct, a 1,500‑point benchmark that combines NextMe‑800 with the multi‑person EgoLife dataset, and evaluate models using an embedding‑based soft edit distance to assess how well personal behavior can be anticipated across abstraction levels and prediction horizons.
The paper introduces DSSM-CRF, an audio‑only architecture for conversational speech emotion recognition that separates cross‑speaker contextual influence from within‑speaker emotion evolution. It uses bidirectional state‑space models to encode fused self‑supervised speech representations at both frame and dialogue scales, then orders each speaker’s utterances into an independent dynamic conditional random field chain. The model achieves state‑of‑the‑art performance on IEMOCAP and MELD, with complementary gains from speaker‑wise factorization and CRF modeling.
The study examines whether personalized latent dynamics can reveal clinically relevant differences even when predictive accuracy is similar. Using a lightweight CNN–Transformer EEG foundation model pretrained on the Temple University EEG Corpus, the authors map EEG representations to a shared latent-state space and fit sparse multinomial logistic transition distributions for each of 198 subjects (99 epilepsy, 99 non‑epilepsy). Results show that epilepsy subjects exhibit denser learned dependency structures at k=4 and k=6, while held‑out log‑likelihood and next‑state prediction are nearly identical between groups, indicating that similar predictive fit does not imply similar learned dynamics.
arXiv:2610.27603v1 Announce Type: new Abstract: Empathetic interaction involves two distinguishable capacities: representing another person's emotional state (cognitive empathy) and generating an app...
The study tackles music enjoyment prediction by treating it as a regression task using EEG data from the MUSIN-G dataset. Six deep learning models were evaluated, with DeepConvNet, CNN‑LSTM, and GNN‑CNN achieving the lowest mean absolute error, while a temporal convolutional network (TCN) showed the highest Pearson correlation with listener ratings. Gradient‑based and occlusion‑based explainability methods were applied to the TCN to identify which time segments within each two‑second window most influence predictions, providing a reproducible cross‑listener benchmark for EEG‑based enjoyment regression.
arXiv:2606. 07707v1 Announce Type: new Abstract: Decoding emotional states from neural signals has been typically framed as a discrete, single-label classification task based on emotionally stable stimuli, a formulation that oversimplifies the continuous, fluid, and co-occurring nature of human affect.
arXiv:2610.18305v1 Announce Type: cross Abstract: The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotion...
arXiv:2607. 01400v1 Announce Type: cross Abstract: Deep multimodal brain-encoding models now predict fMRI responses to naturalistic video with high accuracy.
arXiv:2608. 07518v1 Announce Type: cross Abstract: Longitudinal, in-the-wild, wearable sensing yields day-level physiology, sleep, activity, and environmental streams, whereas affect and cognition are labeled only episodically (per waves).
arXiv:2608. 11656v1 Announce Type: new Abstract: Recent advances in EEG foundation models have demonstrated the potential of large-scale pretraining to enable generalizable neural decoding across subjects, recording environments, and datasets.