Data valuation has become central in the era of data-centric AI. It drives efficient training pipelines and enables objective pricing in data markets by assigning a numeric value to each data point. Most existing data valuation methods estimate the effect of removing individual data points by evaluating changes in model validation performance under in-distribution (ID) settings, as opposed to out-of-distribution (OOD) scenarios where data follow different patterns. Since ID and OOD data behave differently, data valuation methods based on ID loss often fail to generalize to OOD settings, particularly when the validation set contains no OOD data. Furthermore, although OOD-aware methods exist, they involve heavy computational costs, which hinder practical deployment. To address these challenges, we introduce \emph{Eigen-Value} (EV), a plug-and-play data valuation framework for OOD robustness that uses only an ID data subset, including during validation. EV provides a new spectral approximation of domain discrepancy, which is the gap of loss between ID and OOD using ratios of eigenvalues of ID data's covariance matrix. EV then estimates the marginal contribution of each data point to this discrepancy via perturbation theory, alleviating the computational burden. Subsequently, EV plugs into ID loss-based methods by adding an EV term without any additional training loop. We demonstrate that EV achieves improved OOD robustness and stable value rankings across real-world datasets, while remaining computationally lightweight. These results indicate that EV is practical for large-scale settings with domain shift, offering an efficient path to OOD-robust data valuation.

Large language models (LLMs) have demonstrated promising performance in generating diagnostic conclusions from imaging findings, thereby supporting radiology reporting, trainee education, and quality control. However, systematic guidance on how to optimize prompt design across different clinical contexts remains underexplored. Moreover, a comprehensive and standardized framework for assessing the trustworthiness of LLM-generated radiology reports is yet to be established. This study aims to enhance the trustworthiness of LLM-generated liver MRI reports by introducing a Multi-Dimensional Credibility Assessment (MDCA) framework and providing guidance on institution-specific prompt optimization. The proposed framework is applied to evaluate and compare the performance of several advanced LLMs, including Kimi-K2-Instruct-0905, Qwen3-235B-A22B-Instruct-2507, DeepSeek-V3, and ByteDance-Seed-OSS-36B-Instruct, using the SiliconFlow platform.

Continual Learning (CL) is essential for enabling self-evolving large language models (LLMs) to adapt and remain effective amid rapid knowledge growth. Yet, despite its importance, little attention has been given to establishing statistical reliability guarantees for LLMs under CL, particularly in the setting of continual domain pretraining (CDP). Conformal Prediction (CP) has shown promise in offering correctness guarantees for LLMs, but it faces major challenges in CDP: testing data often stems from unknown or shifting domain distributions, under which CP may no longer provide valid guarantees. Moreover, when high coverage is required, CP can yield excessively large prediction sets for unanswerable queries, reducing informativeness. To address these challenges, we introduce an adaptive rejection and non-exchangeable CP framework. Our method first estimates the distribution of questions across domains in the test set using transformer-based clustering, then reweights or resamples the calibration data accordingly. Building on this, adaptive rejection CP allows the LLM to selectively abstain from answering when its confidence or competence shifts significantly. Extensive experiments demonstrate that our framework enhances both the effectiveness and reliability of CP under CDP scenarios. Our code is available at: https://anonymous.4open.science/r/CPCL-8C12/

We introduce Look and Tell, a multimodal dataset for studying referential communication across egocentric and exocentric perspectives. Using Meta Project Aria smart glasses and stationary cameras, we recorded synchronized gaze, speech, and video as 25 participants instructed a partner to identify ingredients in a kitchen. Combined with 3D scene reconstructions, this setup provides a benchmark for evaluating how different spatial representations (2D vs. 3D; ego vs. exo) affect multimodal grounding. The dataset contains 3.67 hours of recordings, including 2,707 richly annotated referential expressions, and is designed to advance the development of embodied agents that can understand and engage in situated dialogue.

Vision Language Models (VLMs) achieve strong performance on many vision-language tasks but often struggle with spatial reasoning--a prerequisite for many applications. Empirically, we find that a dataset produced by a current training data generation pipeline has a 57.6% human validation rate. These rates stem from current limitations: single-image 3D reconstruction introduces cascading modeling errors and requires wide answer tolerances, while caption-based methods require hyper-detailed annotations and suffer from generative hallucinations. We present GRAID, built on the key insight that qualitative spatial relationships can be reliably determined from 2D geometric primitives alone. By operating exclusively on 2D bounding boxes from standard object detectors, GRAID avoids both 3D reconstruction errors and generative hallucinations, resulting in datasets that are of higher quality than existing tools that produce similar datasets as validated by human evaluations. We apply our framework to the BDD100k, NuImages, and Waymo datasets, generating over 8.5 million high-quality VQA pairs creating questions spanning spatial relations, counting, ranking, and size comparisons. We evaluate one of the datasets and find it achieves 91.16% human-validated accuracy--compared to 57.6% on a dataset generated by recent work. Critically, we demonstrate that when trained on GRAID data, models learn spatial reasoning concepts that generalize: models fine-tuned on 6 question types improve on over 10 held-out types, with accuracy gains of 47.5% on BDD and 37.9% on NuImages for Llama 3.2B 11B, and when trained on all questions types, achieve improvements on several existing benchmarks such as BLINK. The GRAID framework, datasets, and additional information can be found on our project page. Vision Language Models (VLMs) have already shown promise in a wide variety of applications, such as medical diagnosis Jin et al. (2024), biology (Maruf et al., 2025), and engineering design (Pi-card et al., 2025). However, despite this promise, a key failure mode of VLMs is that they are poor spatial reasoners, that is, they struggle to understand how objects are located in space and the spatial relationships between them. For example, in medical image analysis, Jin et al. (2024) found that VLMs were unable to recognize that skin lesions shown at different angles were the same pathology. Similarly, in robotics, Wang et al. (2025) found that without integrating explicit spatial relationships, VLMs were unable to produce high-level, executable robotic task plans.

The goal of this thesis is to improve our understanding of the internal mechanisms by which deep artificial neural networks create meaningful representations and are able to generalize. We focus on the challenge of characterizing the semantic content of the hidden representations with unsupervised learning tools, partially developed by us and described in this thesis, which allow harnessing the low-dimensional structure of the data. Chapter 2. introduces Gride, a method that allows estimating the intrinsic dimension of the data as an explicit function of the scale without performing any decimation of the data set. Our approach is based on rigorous distributional results that enable the quantification of uncertainty of the estimates. Moreover, our method is simple and computationally efficient since it relies only on the distances among nearest data points. In Chapter 3, we study the evolution of the probability density across the hidden layers in some state-of-the-art deep neural networks. We find that the initial layers generate a unimodal probability density getting rid of any structure irrelevant to classification. In subsequent layers, density peaks arise in a hierarchical fashion that mirrors the semantic hierarchy of the concepts. This process leaves a footprint in the probability density of the output layer, where the topography of the peaks allows reconstructing the semantic relationships of the categories. In Chapter 4, we study the problem of generalization in deep neural networks: adding parameters to a network that interpolates its training data will typically improve its generalization performance, at odds with the classical bias-variance trade-off. We show that wide neural networks learn redundant representations instead of overfitting to spurious correlation and that redundant neurons appear only if the network is regularized and the training error is zero.

Background: Trustworthy AI serves as a foundational pillar for two major AI ethics conferences: AIES and FAccT. However, current research often adopts techno-centric approaches, focusing primarily on technical attributes such as reliability, robustness, and fairness, while overlooking the sociotechnical dimensions critical to understanding AI trustworthiness in real-world contexts. Objectives: This scoping review aims to examine how the AIES and FAccT communities conceptualize, measure, and validate AI trustworthiness, identifying major gaps and opportunities for advancing a holistic understanding of trustworthy AI systems. Methods: We conduct a scoping review of AIES and FAccT conference proceedings to date, systematically analyzing how trustworthiness is defined, operationalized, and applied across different research domains. Our analysis focuses on conceptualization approaches, measurement methods, verification and validation techniques, application areas, and underlying values. Results: While significant progress has been made in defining technical attributes such as transparency, accountability, and robustness, our findings reveal critical gaps. Current research often predominantly emphasizes technical precision at the expense of social and ethical considerations. The sociotechnical nature of AI systems remains less explored and trustworthiness emerges as a contested concept shaped by those with the power to define it. Conclusions: An interdisciplinary approach combining technical rigor with social, cultural, and institutional considerations is essential for advancing trustworthy AI. We propose actionable measures for the AI ethics community to adopt holistic frameworks that genuinely address the complex interplay between AI systems and society, ultimately promoting responsible technological development that benefits all stakeholders.

Panic attacks are acute episodes of fear and distress, in which timely, appropriate intervention can significantly help individuals regain stability. However, suitable datasets for training such models remain scarce due to ethical and logistical issues. To address this, we introduce PACE, which is a dataset that includes high-distress episodes constructed from first-person narratives, and structured around the principles of Psychological First Aid (PFA). Using this data, we train PACER, a counseling model designed to provide both empathetic and directive support, which is optimized through supervised learning and simulated preference alignment. To assess its effectiveness, we propose PanicEval, a multi-dimensional framework covering general counseling quality and crisis-specific strategies. Experimental results show that PACER outperforms strong baselines in both counselor-side metrics and client affect improvement. Human evaluations further confirm its practical value, with PACER consistently preferred over general, CBT-based, and GPT-4-powered models in panic scenarios (Code is available at https://github.com/JihyunLee1/PanicToCalm ).

We analyse financial stability and welfare impacts associated with the introduction of a Central Bank Digital Currency (CBDC) in a macroeconomic agent-based model. The model considers firms, banks, and households interacting on labour, goods, credit, and interbank markets. Households move their liquidity from deposits to CBDC based on the perceived riskiness of their banks. We find that the introduction of CBDC exacerbates bank-runs and may lead to financial instability phenomena. The effect can be changed by introducing a limit on CBDC holdings. The adoption of CBDC has little effect on macroeconomic variables but the interest rate on loans to firms goes up and credit goes down in a limited way. CBDC leads to a redistribution of wealth from firms and banks to households with a higher bank default rate. CBDC may have negative welfare effects, but a bound on holding enables a welfare improvement.

The prevalence of online learning poses a vital challenge in real-time monitoring of students' concentration. Traditional methods such as questionnaire assessments require manual intervention, and webcam-based monitoring fails to provide accurate insights about learners' mental focus as it is deceived by mere screen fixation without cognitive engagement. Existing BCI-based approaches lack real-time validation and evaluation procedures. To address these limitations, a Brain-Computer Interface (BCI) system is developed using a non-invasive Electroencephalogram (EEG) headband, FocusCalm, to record brainwave activity under attentive and non-attentive states. 20 minutes of data were collected from each of 20 participants watching a pre-recorded educational video. The data validation employed a novel intra-video questionnaire assessment. Subsequently, collected signals were segmented (sliding window), filtered (Butterworth bandpass), and cleaned (removal of high-amplitude and EOG artifacts such as eye blinks). Time, frequency, wavelet, and statistical features were extracted, followed by recursive feature elimination (RFE) with support vector machines (SVMs) to classify attention and non-attention states. The leave-one-subject-out (LOSO) cross-validation accuracy was found to be 88.77%. The system provides feedback alerts upon detection of a non-attention state and maintains focus profile logs. A pilot study was conducted to evaluate the effectiveness of real-time feedback. Five participants underwent a 10-minute session comprising a 5-minute baseline phase devoid of feedback, succeeded by a 5-minute feedback phase, during which alerts were activated if participants exhibited inattention for approximately 8 consecutive seconds. A paired t-test (t = 5.73, p = 0.007) indicated a statistically significant improvement in concentration during the feedback phase.