Emily Zhou

Aditya Kommineni, Emily Zhou, Kleanthis Avramidis et al.

Evaluating foundation models under appropriate adaptation settings is essential for understanding the quality and transferability of the learned representations. Recent EEG foundation models have demonstrated promising transfer capabilities across tasks and datasets, motivating their growing use in neurotechnology and clinical applications. However, these models are typically evaluated under full fine-tuning on well-curated downstream datasets, a setting that does not reflect biomedical domain constraints such as limited labeled data, reduced sensor coverage, or parameter-efficient adaptation. In this work, we propose a multi-dimensional evaluation framework for assessing EEG models under realistic low-resource conditions. Empirical analysis of both supervised EEG models and recent EEG foundation models, including LaBraM, CSBrain, and CBraMod, across 6 different datasets is performed under the proposed multi-dimensional evaluation framework. We find that EEG foundation models consistently provide performance gains on long-context tasks such as sleep stage prediction and mental health state classification. In contrast, for short-window Brain Computer Interface style tasks, supervised models achieve comparable despite having substantially fewer parameters. Additional analyses demonstrate that current foundation models provide limited robustness to short-window tasks and channel constrained settings. Together, these findings motivate the use of multi-dimensional evaluation protocols that characterize model behavior under realistic use constraints.

Aditya Kommineni, Emily Zhou, Kleanthis Avramidis et al.

EEG foundation models, pre-trained on large-scale unlabelled EEG data, have emerged as a promising direction towards learning generalizable EEG representations. Despite showing positive results in data-rich regimes, they often fail to outperform significantly smaller supervised models in low-resource settings compared to fully supervised models. We provide a mechanistic account of this shortcoming, attributing it to a fundamental mismatch between reconstruction-based pretext tasks and the idiosyncratic spectral structure of EEG signals, which decompose into distinct high-power aperiodic and low-power oscillatory components. Using controlled, synthetically-generated EEG inputs, we demonstrate that EEG foundation model embeddings are biased to capture the aperiodic components of the EEG signal while under-representing oscillatory components, particularly at higher frequencies. Additionally, linear probe evaluations on real-world BCI datasets further reveal that embeddings encode subject identity more strongly than task-relevant information, thereby reinforcing the low-frequency and aperiodic component bias in foundation model embeddings trained primarily on reconstruction based objectives. Together, these findings elucidate a failure mode in reconstruction based EEG foundation models and motivate future work to incorporate auxiliary losses explicitly targeting high-frequency oscillatory structure as a path toward more capable and generalizable EEG representations.

Marcus Ma, Emily Zhou, Leonard Ludwig et al.

We study when, where, and why 978 Holocaust survivors smile in video testimonies. We create an automatic smile detection model from facial features with an F1 of 85% and annotate detected smiles under two established taxonomies of smiling. We produce narrative features on 1,083,417 transcript sentences as well as emotional valence from three different modalities: audio, eye gaze, and text transcript. Smiling rates are significantly correlated with specific semantic topics, narrative structures, and temporal syntaxes across the entire corpus. Smiles often occur during periods of intense negative affect; these negative-affect smiles improve the valence trajectory of surrounding sentences significantly across all three modalities. Smiling reduces eye dynamics and blink rates, and the strength of both of these effects is also modulated by narrative valence. Taken together, we conclude that smiling plays a critical role in regulating emotion and social interaction during traumatic recollection.

Emily Zhou, Marcus Ma, Kleanthis Avramidis et al.

Eye movement and memory retrieval are deeply and bidirectionally intertwined, however existing literature is generally confined to controlled lab settings. We investigate the relationship between eye gaze and memory recall in free-form autobiographical recall, which comprises both autonoetic consciousness -- the ability to mentally place oneself in the past or future -- and various affective states. Using a large video corpus of semi-naturalistic interviews with Holocaust survivors (N = 806), we examine eye movements with respect to episodic, semantic, affective, and temporal dimensions of traumatic and highly emotional autobiographical recall. We observe gaze patterns vary significantly across certain temporal contexts, most prominently in vertical eye movements. We additionally train intra-subject sequence models to predict temporal context of sentences from segments of gaze features, and find that eye movements entirely preceding sentence onset are sufficient for prediction. Our results corroborate prior findings in literature linking eye movements to memory in controlled and semi-structured settings, reinforcing the role of eye gaze in retrieving and constructing memories, especially in highly emotional and remote memory recall.

Lihan Zha, Apurva Badithela, Michael Zhang et al.

Generalist imitation learning policies trained on large datasets show great promise for solving diverse manipulation tasks. However, to ensure generalization to different conditions, policies need to be trained with data collected across a large set of environmental factor variations (e.g., camera pose, table height, distractors) $-$ a prohibitively expensive undertaking, if done exhaustively. We introduce a principled method for deciding what data to collect and how much to collect for each factor by constructing factored scaling curves (FSC), which quantify how policy performance varies as data scales along individual or paired factors. These curves enable targeted data acquisition for the most influential factor combinations within a given budget. We evaluate the proposed method through extensive simulated and real-world experiments, across both training-from-scratch and fine-tuning settings, and show that it boosts success rates in real-world tasks in new environments by up to 26% over existing data-collection strategies. We further demonstrate how factored scaling curves can effectively guide data collection using an offline metric, without requiring real-world evaluation at scale.

Emily Zhou, Mohammad Soleymani, Maja J. Matarić

Recent works have demonstrated the effectiveness of machine learning (ML) techniques in detecting anxiety and stress using physiological signals, but it is unclear whether ML models are learning physiological features specific to stress. To address this ambiguity, we evaluated the generalizability of physiological features that have been shown to be correlated with anxiety and stress to high-arousal emotions. Specifically, we examine features extracted from electrocardiogram (ECG) and electrodermal (EDA) signals from the following three datasets: Anxiety Phases Dataset (APD), Wearable Stress and Affect Detection (WESAD), and the Continuously Annotated Signals of Emotion (CASE) dataset. We aim to understand whether these features are specific to anxiety or general to other high-arousal emotions through a statistical regression analysis, in addition to a within-corpus, cross-corpus, and leave-one-corpus-out cross-validation across instances of stress and arousal. We used the following classifiers: Support Vector Machines, LightGBM, Random Forest, XGBoost, and an ensemble of the aforementioned models. We found that models trained on an arousal dataset perform relatively well on a previously unseen stress dataset, and vice versa. Our experimental results suggest that the evaluated models may be identifying emotional arousal instead of stress. This work is the first cross-corpus evaluation across stress and arousal from ECG and EDA signals, contributing new findings about the generalizability of stress detection.

Tenny Yin, Zhiting Mei, Tao Sun et al.

Language-instructed active object localization is a critical challenge for robots, requiring efficient exploration of partially observable environments. However, state-of-the-art approaches either struggle to generalize beyond demonstration datasets (e.g., imitation learning methods) or fail to generate physically grounded actions (e.g., VLMs). To address these limitations, we introduce WoMAP (World Models for Active Perception): a recipe for training open-vocabulary object localization policies that: (i) uses a Gaussian Splatting-based real-to-sim-to-real pipeline for scalable data generation without the need for expert demonstrations, (ii) distills dense rewards signals from open-vocabulary object detectors, and (iii) leverages a latent world model for dynamics and rewards prediction to ground high-level action proposals at inference time. Rigorous simulation and hardware experiments demonstrate WoMAP's superior performance in a broad range of zero-shot object localization tasks, with more than 9x and 2x higher success rates compared to VLM and diffusion policy baselines, respectively. Further, we show that WoMAP achieves strong generalization and sim-to-real transfer on a TidyBot.

Emily Zhou, Khushboo Khatri, Yixue Zhao et al.

The field of affective computing focuses on recognizing, interpreting, and responding to human emotions, and has broad applications across education, child development, and human health and wellness. However, developing affective computing pipelines remains labor-intensive due to the lack of software frameworks that support multimodal, multi-domain emotion recognition applications. This often results in redundant effort when building pipelines for different applications. While recent frameworks attempt to address these challenges, they remain limited in reducing manual effort and ensuring cross-domain generalizability. We introduce AffectEval, a modular and customizable framework to facilitate the development of affective computing pipelines while reducing the manual effort and duplicate work involved in developing such pipelines. We validate AffectEval by replicating prior affective computing experiments, and we demonstrate that our framework reduces programming effort by up to 90%, as measured by the reduction in raw lines of code.

Sheng Yu, Narjes Nourzad, Randye J. Semple et al.

The COVID-19 pandemic has intensified the urgency for effective and accessible mental health interventions in people's daily lives. Mobile Health (mHealth) solutions, such as AI Chatbots and Mindfulness Apps, have gained traction as they expand beyond traditional clinical settings to support daily life. However, the effectiveness of current mHealth solutions is impeded by the lack of context-awareness, personalization, and modularity to foster their reusability. This paper introduces CAREForMe, a contextual multi-armed bandit (CMAB) recommendation framework for mental health. Designed with context-awareness, personalization, and modularity at its core, CAREForMe harnesses mobile sensing and integrates online learning algorithms with user clustering capability to deliver timely, personalized recommendations. With its modular design, CAREForMe serves as both a customizable recommendation framework to guide future research, and a collaborative platform to facilitate interdisciplinary contributions in mHealth research. We showcase CAREForMe's versatility through its implementation across various platforms (e.g., Discord, Telegram) and its customization to diverse recommendation features.