arXiv subjects

Gemma Roig

Publications and source records attributed to Gemma Roig.

At least 19 recordsLinked to original sources

arXiv2026

Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in Online Learning

The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distinct behavioral, emotional, and cognitive states. A reliable prediction requires bringing together different types of behavioral signals as well as expressive cues. Through our analysis of the CASED dataset, it is clear that engagement prediction gets even harder due to the high inter-person variability as well as the subjectivity of the engagement annotation. To tackle these challenges, we develop a multimodal framework that integrates the implicit spatiotemporal features extracted from pretrained video, audio, and image encoders along with structured behavioral modalities like head pose, gaze, facial action units, emotion, and wavelet-based audio features. We integrate these modalities via a Perceiver IO latent bottleneck. Moreover, student and instructor personalities are modeled as variational posteriors over learnable embeddings to enable partial pooling across participants. We employ evidential regression and spectral-normalized Gaussian process classification heads for uncertainty-aware prediction to further improve robustness and calibration. Benchmark on the CASED challenge test set shows that all participating methods converge near random-chance performance, revealing the difficulty of the dataset. In this highly ambiguous regime, our framework achieves competitive performance while uniquely offering well-calibrated uncertainty metrics, demonstrating that reliable risk-quantification is an essential prerequisite for deploying engagement models in real-world educational tools.

cs.CV↗

arXiv2026

Large language model-assisted discovery of cohorts from scientific literature

Background: Planning multi-study analyses requires identifying cohorts with the relevant participants, phenotypes, and data modalities. This process commonly relies on prior knowledge, cohort catalogues, and manual literature searches. We developed a complementary question-driven framework that searches relevant scientific literature and extracts explicit cohort names. Methods: The framework first generates multiple PubMed queries from configurable vocabularies and templates and retrieves the resulting scientific literature automatically through the PubMed API. A large language model then screens the retrieved titles and abstracts and extracts explicit cohort names using a prompt tailored to the research question. The extracted names are deduplicated with human review. Configurable code, prompts, and example outputs are available at https://gitlab.rz.uni-frankfurt.de/cap_molgenlab/literature-cohort-discovery. Evaluation: As a use case, we applied the framework to youth aggression genetics. From 5,400 generated PubMed queries, the framework retrieved 5,254 unique records and identified 188 candidate cohorts. Manual screening using predefined criteria, including participant age and genetic-data availability, retained 44 eligible cohorts. Automated LLM-based name extraction was within the agreement range of human annotators. We also searched four established cohort catalogues using the same research question. Their combined results contained 27 of the 44 eligible cohorts, while 17 were not returned by any cohort catalogue search. Conclusion: The framework converts research-question-specific vocabulary into screenable cohort inventories via a large, automated literature search. It can be adapted across populations, phenotypes, data modalities, and study designs, and provides a literature-based complement to curated cohort catalogues.

cs.IR↗

arXiv2026

Mechanisms of Object Localization in Vision-Language Models

Visually-grounded language models (VLMs) are highly effective in linking visual and textual information, yet they often struggle with basic classification and localization tasks. While classification mechanisms have been studied more extensively, the processes that support object localization remain poorly understood. In this work, we investigate two representative families, LLaVA-1.5 and InternVL-3.5, using a suite of mechanistic interpretability tools, including token ablations, attention knockout, and causal mediation analysis. We find that localization is driven by a containerization mechanism in which object-aligned tokens define the spatial extent of the object, while the semantic arrangement of tokens within those boundaries is largely irrelevant to the predicted box. Only a very small set of attention heads mediates the causal effect for both classification and localization, concentrating in early-mid layers for LLaVA and mid-late layers for InternVL. The two tasks share some early processing but ultimately depend on largely distinct specialized heads. Overall, we provide the first layer- and head-level account of localization in VLMs, revealing narrow computational pathways that can guide future model design and grounding objectives.

cs.CV↗

arXiv2026

MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space

Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive their predictions. Existing robustness benchmarks provide important stress tests, but typically manipulate global 2D image properties, rely on entangled real-world variation, or cover only a limited set of 3D objects and scene parameters. We introduce MAPS (Manifolds of Artificial Parametric Scenes), a scalable instrument for controlled attribution of vision model behavior to scene parameters. MAPS comprises 2,618 curated photorealistic 3D meshes validated for recognizability across 560 ImageNet classes and provides a Blender-based rendering pipeline for on-demand image generation under continuous variation of nine independent scene-factors spanning background, camera, and lighting, extensible to other factors. To showcase its applicability, we use MAPS to evaluate 20 convolutional and transformer-based models by quantifying their reliance on these scene factors through regression-based sensitivity analysis. We find a near-universal failure axis across all tested architectures: camera distance and elevation consistently dominate recognition failure regardless of ImageNet accuracy. However, the full sensitivity structure reveals that modern CNNs and transformers cluster together, distinct from older architectures, suggesting that fine-grained architectural design choices, rather than the coarse CNN-versus-transformer distinction, are the stronger determinant of sensitivity profiles.

cs.CV↗

arXiv2026

Shortcut Mitigation via Spurious-Positive Samples

Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combinations of (spurious) attributes and classes, in the training data. However, these requirements are rarely met in practice. We instead propose a method for targeted model analysis to identify a small set of instances in which the model relies on spurious attributes. Using that set and following ``this feature should not be used for prediction'' reasoning, we identify highly relevant neurons in an intermediate layer and regularize their impact. This ensures that models learn to depend on informative features rather than being right for the wrong reasons, thereby improving robustness without requiring additional balanced held-out data or annotations.

cs.LG↗

arXiv2026

Evaluation of Randomization through Style Transfer for Enhanced Domain Generalization

Deep learning models for computer vision often suffer from poor generalization when deployed in real-world settings, especially when trained on synthetic data due to the well-known Sim2Real gap. Despite the growing popularity of style transfer as a data augmentation strategy for domain generalization, the literature contains unresolved contradictions regarding three key design axes: the diversity of the style pool, the role of texture complexity, and the choice of style source. We present a systematic empirical study that isolates and evaluates each of these factors for driving scene understanding, resolving inconsistencies in prior work. Our findings show that (i) expanding the style pool yields larger gains than repeated augmentation with few styles, (ii) texture complexity has no significant effect when the pool is sufficiently large, and (iii) diverse artistic styles outperform domain-aligned alternatives. Guided by these insights, we derive StyleMixDG (Style-Mixing for Domain Generalization), a lightweight, model-agnostic augmentation recipe that requires no architectural modifications or additional losses. Evaluated on the GTAV $\rightarrow$ {BDD100k, Cityscapes, Mapillary Vistas} benchmark, StyleMixDG demonstrates consistent improvements over strong baselines, confirming that the empirically identified design principles translate into practical gains. The code will be released on GitHub.

cs.CV↗

arXiv2026

Contextual inference from single objects in Vision-Language models

How much scene context a single object carries is a well-studied question in human scene perception, yet how this capacity is organized in vision-language models (VLMs) remains poorly understood, with direct implications for the robustness of these models. We investigate this question through a systematic behavioral and mechanistic analysis of contextual inference from single objects. Presenting VLMs with single objects on masked backgrounds, we probe their ability to infer both fine-grained scene category and coarse superordinate context (indoor vs. outdoor). We found that single objects support above-chance inference at both levels, with performance modulated by the same object properties that predict human scene categorization. Object identity, scene, and superordinate predictions are partially dissociable: accurate inference at one level neither requires nor guarantees accurate inference at the others, and the degree of coupling differs markedly across models. Mechanistically, object representations that remain stable when background context is removed are more predictive of successful contextual inference. Scene and superordinate schemas are grounded in fundamentally different ways: scene identity is encoded in image tokens throughout the network, while superordinate information emerges only late or not at all. Together, these results reveal that the organization of contextual inference in VLMs is more complex than accuracy alone suggests, with behavioral and mechanistic signatures

cs.CV↗

arXiv2026

Temporal Slowness in Central Vision Drives Semantic Object Learning

Humans acquire semantic object representations from egocentric visual streams with minimal supervision, but the underlying mechanisms remain unclear. Importantly, the visual system only processes the center of its field of view with high resolution and it learns similar representations for visual inputs occurring close in time. This emphasizes slowly changing information around gaze locations. This study investigates the role of central vision and slowness learning in the formation of semantic object representations from human-like visual experience. We simulate five months of human-like visual experience using the Ego4D dataset and a state-of-the-art gaze prediction model. We extract image crops around predicted gaze locations to train a time-contrastive Self-Supervised Learning model. Our results show that exploiting temporal slowness when learning from central visual field experience improves the encoding of different facets of object semantics. Specifically, focusing on central vision strengthens the extraction of foreground object features, while considering temporal slowness, especially in conjunction with eye movements, allows the model to encode broader semantic information about objects. These findings provide new insights into the mechanisms by which humans may develop semantic object representations from natural visual experience. Our code will be made public upon acceptance. Code is available at https://github.com/t9s9/central-vision-ssl.

cs.CV↗

arXiv2025

The Representational Alignment between Humans and Language Models is implicitly driven by a Concreteness Effect

The nouns of our language refer to either concrete entities (like a table) or abstract concepts (like justice or love), and cognitive psychology has established that concreteness influences how words are processed. Accordingly, understanding how concreteness is represented in our mind and brain is a central question in psychology, neuroscience, and computational linguistics. While the advent of powerful language models has allowed for quantitative inquiries into the nature of semantic representations, it remains largely underexplored how they represent concreteness. Here, we used behavioral judgments to estimate semantic distances implicitly used by humans, for a set of carefully selected abstract and concrete nouns. Using Representational Similarity Analysis, we find that the implicit representational space of participants and the semantic representations of language models are significantly aligned. We also find that both representational spaces are implicitly aligned to an explicit representation of concreteness, which was obtained from our participants using an additional concreteness rating task. Importantly, using ablation experiments, we demonstrate that the human-to-model alignment is substantially driven by concreteness, but not by other important word characteristics established in psycholinguistics. These results indicate that humans and language models converge on the concreteness dimension, but not on other dimensions.

cs.CL↗

arXiv2025

Follow the MEP: Scalable Neural Representations for Minimum-Energy Path Discovery in Molecular Systems

Characterizing conformational transitions in physical systems remains a fundamental challenge, as traditional sampling methods struggle with the high-dimensional nature of molecular systems and high-energy barriers between stable states. These rare events often represent the most biologically significant processes, yet may require months of continuous simulation to observe. One way to understand the function and mechanics of such systems is through the minimum energy path (MEP), which represents the most probable transition pathway between stable states in the high-friction, low-temperature limit. We present a method that reformulates MEP discovery as a fast and scalable neural optimization problem. By representing paths as implicit neural representations and training with differentiable molecular force fields, our method discovers transition pathways without expensive sampling. Our approach scales to large biomolecular systems through a simple loss function derived from the path's likelihood via the Onsager-Machlup action and a scalable new architecture, AdaPath. We demonstrate this approach on two proteins, including an explicitly hydrated BPTI system with more than 3,500 atoms. Our method identifies a MEP that captures the same conformational change observed in a millisecond-scale molecular dynamics (MD) simulation in just minutes on a standard GPU, rather than weeks on a specialized cluster.

physics.chem-ph↗

arXiv2025

Cognitive Neural Architecture Search Reveals Hierarchical Entailment

Recent research has suggested that the brain is more shallow than previously thought, challenging the traditionally assumed hierarchical structure of the ventral visual pathway. Here, we demonstrate that optimizing convolutional network architectures for brain-alignment via evolutionary neural architecture search results in models with clear representational hierarchies. Despite having random weights, the identified models achieve brain-alignment scores surpassing even those of pretrained classification models - as measured by both regression and representational similarity analysis. Furthermore, through traditional supervised training, architectures optimized for alignment with late ventral regions become competitive classification models. These findings suggest that hierarchical structure is a fundamental mechanism of primate visual processing. Finally, this work demonstrates the potential of neural architecture search as a framework for computational cognitive neuroscience research that could reduce the field's reliance on manually designed convolutional networks.

cs.NE↗

arXiv2025

Human Gaze Boosts Object-Centered Representation Learning

Recent self-supervised learning (SSL) models trained on human-like egocentric visual inputs substantially underperform on image recognition tasks compared to humans. These models train on raw, uniform visual inputs collected from head-mounted cameras. This is different from humans, as the anatomical structure of the retina and visual cortex relatively amplifies the central visual information, i.e. around humans' gaze location. This selective amplification in humans likely aids in forming object-centered visual representations. Here, we investigate whether focusing on central visual information boosts egocentric visual object learning. We simulate 5-months of egocentric visual experience using the large-scale Ego4D dataset and generate gaze locations with a human gaze prediction model. To account for the importance of central vision in humans, we crop the visual area around the gaze location. Finally, we train a time-based SSL model on these modified inputs. Our experiments demonstrate that focusing on central vision leads to better object-centered representations. Our analysis shows that the SSL model leverages the temporal dynamics of the gaze movements to build stronger visual representations. Overall, our work marks a significant step toward bio-inspired learning of visual representations.

cs.CV↗

arXiv2025

Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers

Shortcut learning, i.e., a model's reliance on undesired features not directly relevant to the task, is a major challenge that severely limits the applications of machine learning algorithms, particularly when deploying them to assist in making sensitive decisions, such as in medical diagnostics. In this work, we leverage recent advancements in machine learning to create an unsupervised framework that is capable of both detecting and mitigating shortcut learning in transformers. We validate our method on multiple datasets. Results demonstrate that our framework significantly improves both worst-group accuracy (samples misclassified due to shortcuts) and average accuracy, while minimizing human annotation effort. Moreover, we demonstrate that the detected shortcuts are meaningful and informative to human experts, and that our framework is computationally efficient, allowing it to be run on consumer hardware.

cs.LG↗

arXiv2024

The Algonauts Project 2025 Challenge: How the Human Brain Makes Sense of Multimodal Movies

There is growing symbiosis between artificial and biological intelligence sciences: neural principles inspire new intelligent machines, which are in turn used to advance our theoretical understanding of the brain. To promote further collaboration between biological and artificial intelligence researchers, we introduce the 2025 edition of the Algonauts Project challenge: How the Human Brain Makes Sense of Multimodal Movies (https://algonautsproject.com/). In collaboration with the Courtois Project on Neuronal Modelling (CNeuroMod), this edition aims to bring forth a new generation of brain encoding models that are multimodal and that generalize well beyond their training distribution, by training them on the largest dataset of fMRI responses to movie watching available to date. Open to all, the 2025 challenge provides transparent, directly comparable results through a public leaderboard that is updated automatically after each submission to facilitate rapid model assessment and guide development. The challenge will end with a session at the 2025 Cognitive Computational Neuroscience (CCN) conference that will feature winning models. We welcome researchers interested in collaborating with the Algonauts Project by contributing ideas and datasets for future challenges.

q-bio.NC↗

arXiv2024

On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Process

Knowledge distillation (KD) remains challenging due to the opaque nature of the knowledge transfer process from a Teacher to a Student, making it difficult to address certain issues related to KD. To address this, we proposed UniCAM, a novel gradient-based visual explanation method, which effectively interprets the knowledge learned during KD. Our experimental results demonstrate that with the guidance of the Teacher's knowledge, the Student model becomes more efficient, learning more relevant features while discarding those that are not relevant. We refer to the features learned with the Teacher's guidance as distilled features and the features irrelevant to the task and ignored by the Student as residual features. Distilled features focus on key aspects of the input, such as textures and parts of objects. In contrast, residual features demonstrate more diffused attention, often targeting irrelevant areas, including the backgrounds of the target objects. In addition, we proposed two novel metrics: the feature similarity score (FSS) and the relevance score (RS), which quantify the relevance of the distilled knowledge. Experiments on the CIFAR10, ASIRRA, and Plant Disease datasets demonstrate that UniCAM and the two metrics offer valuable insights to explain the KD process.

cs.CV↗

arXiv2024

Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG

In contrast to human vision, artificial neural networks (ANNs) remain relatively susceptible to adversarial attacks. To address this vulnerability, efforts have been made to transfer inductive bias from human brains to ANNs, often by training the ANN representations to match their biological counterparts. Previous works relied on brain data acquired in rodents or primates using invasive techniques, from specific regions of the brain, under non-natural conditions (anesthetized animals), and with stimulus datasets lacking diversity and naturalness. In this work, we explored whether aligning model representations to human EEG responses to a rich set of real-world images increases robustness to ANNs. Specifically, we trained ResNet50-backbone models on a dual task of classification and EEG prediction; and evaluated their EEG prediction accuracy and robustness to adversarial attacks. We observed significant correlation between the networks' EEG prediction accuracy, often highest around 100 ms post stimulus onset, and their gains in adversarial robustness. Although effect size was limited, effects were consistent across different random initializations and robust for architectural variants. We further teased apart the data from individual EEG channels and observed strongest contribution from electrodes in the parieto-occipital regions. The demonstrated utility of human EEG for such tasks opens up avenues for future efforts that scale to larger datasets under diverse stimuli conditions with the promise of stronger effects.

cs.LG↗

arXiv2024

FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks

Explainability in artificial intelligence (XAI) remains a crucial aspect for fostering trust and understanding in machine learning models. Current visual explanation techniques, such as gradient-based or class-activation-based methods, often exhibit a strong dependence on specific model architectures. Conversely, perturbation-based methods, despite being model-agnostic, are computationally expensive as they require evaluating models on a large number of forward passes. In this work, we introduce Foveation-based Explanations (FovEx), a novel XAI method inspired by human vision. FovEx seamlessly integrates biologically inspired perturbations by iteratively creating foveated renderings of the image and combines them with gradient-based visual explorations to determine locations of interest efficiently. These locations are selected to maximize the performance of the model to be explained with respect to the downstream task and then combined to generate an attribution map. We provide a thorough evaluation with qualitative and quantitative assessments on established benchmarks. Our method achieves state-of-the-art performance on both transformers (on 4 out of 5 metrics) and convolutional models (on 3 out of 5 metrics), demonstrating its versatility among various architectures. Furthermore, we show the alignment between the explanation map produced by FovEx and human gaze patterns (+14\% in NSS compared to RISE, +203\% in NSS compared to GradCAM). This comparison enhances our confidence in FovEx's ability to close the interpretation gap between humans and machines.

cs.CV↗

arXiv2024

Classification of freshwater snails of the genus Radomaniola with multimodal triplet networks

In this paper, we present our first proposal of a machine learning system for the classification of freshwater snails of the genus Radomaniola. We elaborate on the specific challenges encountered during system design, and how we tackled them; namely a small, very imbalanced dataset with a high number of classes and high visual similarity between classes. We then show how we employed triplet networks and the multiple input modalities of images, measurements, and genetic information to overcome these challenges and reach a performance comparable to that of a trained domain expert.

cs.CV↗