High-quality test items are essential for educational assessments, particularly within Item Response Theory (IRT). Traditional validation methods rely on resource-intensive pilot testing to estimate item difficulty and discrimination. More recently, Item-Writing Flaw (IWF) rubrics emerged as a domain-general approach for evaluating test items based on textual features. However, their relationship to IRT parameters remains underexplored. To address this gap, we conducted a study involving over 7,000 multiple-choice questions across various STEM subjects (e.g., math and biology). Using an automated approach, we annotated each question with a 19-criteria IWF rubric and studied relationships to data-driven IRT parameters. Our analysis revealed statistically significant links between the number of IWFs and IRT difficulty and discrimination parameters, particularly in life and physical science domains. We further observed how specific IWF criteria can impact item quality more and less severely (e.g., negative wording vs. implausible distractors). Overall, while IWFs are useful for predicting IRT parameters--particularly for screening low-difficulty MCQs--they cannot replace traditional data-driven validation methods. Our findings highlight the need for further research on domain-general evaluation rubrics and algorithms that understand domain-specific content for robust item validation.

Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existing continual learning approaches in the literature rely on heuristics and do not provide learning guarantees for the continual learning setup. In this paper, we present a new method called 'Continual Pick-to-Learn' (CoP2L), which is able to retain the most representative samples for each task in an efficient way. The algorithm is adapted from the Pick-to-Learn algorithm, rooted in the sample compression theory. This allows us to provide high-confidence upper bounds on the generalization loss of the learned predictors, numerically computable after every update of the learned model. We also empirically show on several standard continual learning benchmarks that our algorithm is able to outperform standard experience replay, significantly mitigating catastrophic forgetting.

We seek to extract a temporally consistent 6D pose trajectory of a manipulated object from an Internet instructional video. This is a challenging set-up for current 6D pose estimation methods due to uncontrolled capturing conditions, subtle but dynamic object motions, and the fact that the exact mesh of the manipulated object is not known. To address these challenges, we present the following contributions. First, we develop a new method that estimates the 6D pose of any object in the input image without prior knowledge of the object itself. The method proceeds by (i) retrieving a CAD model similar to the depicted object from a large-scale model database, (ii) 6D aligning the retrieved CAD model with the input image, and (iii) grounding the absolute scale of the object with respect to the scene. Second, we extract smooth 6D object trajectories from Internet videos by carefully tracking the detected objects across video frames. The extracted object trajectories are then retargeted via trajectory optimization into the configuration space of a robotic manipulator. Third, we thoroughly evaluate and ablate our 6D pose estimation method on YCB-V and HOPE-Video datasets as well as a new dataset of instructional videos manually annotated with approximate 6D object trajectories. We demonstrate significant improvements over existing state-of-the-art RGB 6D pose estimation methods. Finally, we show that the 6D object motion estimated from Internet videos can be transferred to a 7-axis robotic manipulator both in a virtual simulator as well as in a real world set-up. We also successfully apply our method to egocentric videos taken from the EPIC-KITCHENS dataset, demonstrating potential for Embodied AI applications.

Multimodal information-gathering settings, where users collaborate with AI in dynamic environments, are increasingly common. These involve complex processes with textual and multimodal interactions, often requiring additional structural information via cost-incurring requests. AI helpers lack access to users' true goals, beliefs, and preferences and struggle to integrate diverse information effectively. We propose a social continual learning framework for causal knowledge acquisition and collaborative decision-making. It focuses on autonomous agents learning through dialogues, question-asking, and interaction in open, partially observable environments. A key component is a natural language oracle that answers the agent's queries about environmental mechanisms and states, refining causal understanding while balancing exploration or learning, and exploitation or knowledge use. Evaluation tasks inspired by developmental psychology emphasize causal reasoning and question-asking skills. They complement benchmarks by assessing the agent's ability to identify knowledge gaps, generate meaningful queries, and incrementally update reasoning. The framework also evaluates how knowledge acquisition costs are amortized across tasks within the same environment. We propose two architectures: 1) a system combining Large Language Models (LLMs) with the ReAct framework and question-generation, and 2) an advanced system with a causal world model, symbolic, graph-based, or subsymbolic, for reasoning and decision-making. The latter builds a causal knowledge graph for efficient inference and adaptability under constraints. Challenges include integrating causal reasoning into ReAct and optimizing exploration and question-asking in error-prone scenarios. Beyond applications, this framework models developmental processes combining causal reasoning, question generation, and social learning.

We introduce and study the spherical dimension, a natural topological relaxation of the VC dimension that unifies several results in learning theory where topology plays a key role in the proofs. The spherical dimension is defined by extending the set of realizable datasets (used to define the VC dimension) to the continuous space of realizable distributions. In this space, a shattered set of size d (in the VC sense) is completed into a continuous object, specifically a d-dimensional sphere of realizable distributions. The spherical dimension is then defined as the dimension of the largest sphere in this space. Thus, the spherical dimension is at least the VC dimension. The spherical dimension serves as a common foundation for leveraging the Borsuk-Ulam theorem and related topological tools. We demonstrate the utility of the spherical dimension in diverse applications, including disambiguations of partial concept classes, reductions from classification to stochastic convex optimization, stability and replicability, and sample compression schemes. Perhaps surprisingly, we show that the open question posed by Alon, Hanneke, Holzman, and Moran (FOCS 2021) of whether there exist non-trivial disambiguations for halfspaces with margin is equivalent to the basic open question of whether the VC and spherical dimensions are finite together.

Generative language models are increasingly being subjected to psychometric questionnaires intended for human testing, in efforts to establish their traits, as benchmarks for alignment, or to simulate participants in social science experiments. While this growing body of work sheds light on the likeness of model responses to those of humans, concerns are warranted regarding the rigour and reproducibility with which these experiments may be conducted. Instabilities in model outputs, sensitivity to prompt design, parameter settings, and a large number of available model versions increase documentation requirements. Consequently, generalization of findings is often complex and reproducibility is far from guaranteed. In this paper, we present R.U.Psycho, a framework for designing and running robust and reproducible psychometric experiments on generative language models that requires limited coding expertise. We demonstrate the capability of our framework on a variety of psychometric questionnaires, which lend support to prior findings in the literature. R.U.Psycho is available as a Python package at https://github.com/julianschelb/rupsycho.

This research introduces a comprehensive system based on state-of-the-art natural language processing, semantic embedding, and efficient search techniques for retrieving similarities and thus generating actionable insights from raw textual information. The system automatically extracts and aggregates normalized competencies from multiple documents (such as policy files and curricula vitae) and creates strong relationships between recognized competencies, occupation profiles, and related learning courses. To validate its performance, we conducted a multi-tier evaluation that included both explicit and implicit skill references in synthetic and real-world documents. The results showed near-human-level accuracy, with F1 scores exceeding 0.95 for explicit skill detection and above 0.93 for implicit mentions. The system thereby establishes a sound foundation for supporting in-depth collaboration across the AE4RIA network. The methodology involves a multi-stage pipeline based on extensive preprocessing and data cleaning, semantic embedding and segmentation via SentenceTransformer, and skill extraction using a FAISS-based search method. The extracted skills are associated with occupation frameworks (as formulated in the ESCO ontology) and with learning paths offered through the Sustainable Development Goals Academy. Moreover, interactive visualization software, implemented with Dash and Plotly, presents graphs and tables for real-time exploration and informed decision-making by those involved in policymaking, training and learning supply, career transitions, and recruitment. Overall, this system, backed by rigorous validation, offers promising prospects for improved policymaking, human resource development, and lifelong learning by providing structured and actionable insights from raw, complex textual information.

Scaling laws are a critical component of the LLM development pipeline, most famously as a way to forecast training decisions such as 'compute-optimally' trading-off parameter count and dataset size, alongside a more recent growing list of other crucial decisions. In this work, we ask whether compute-optimal scaling behaviour can be skill-dependent. In particular, we examine knowledge and reasoning-based skills such as knowledge-based QA and code generation, and we answer this question in the affirmative: scaling laws are skill-dependent. Next, to understand whether skill-dependent scaling is an artefact of the pretraining datamix, we conduct an extensive ablation of different datamixes and find that, also when correcting for datamix differences, knowledge and code exhibit fundamental differences in scaling behaviour. We conclude with an analysis of how our findings relate to standard compute-optimal scaling using a validation set, and find that a misspecified validation set can impact compute-optimal parameter count by nearly 50%, depending on its skill composition.

The success of multi-modal large language models (MLLMs) has been largely attributed to the large-scale training data. However, the training data of many MLLMs is unavailable due to privacy concerns. The expensive and labor-intensive process of collecting multi-modal data further exacerbates the problem. Is it possible to synthesize multi-modal training data automatically without compromising diversity and quality? In this paper, we propose a new method, Oasis, to synthesize high-quality multi-modal data with only images. Oasis breaks through traditional methods by prompting only images to the MLLMs, thus extending the data diversity by a large margin. Our method features a delicate quality control method which ensures the data quality. We collected over 500k data and conducted incremental experiments on LLaVA-NeXT. Extensive experiments demonstrate that our method can significantly improve the performance of MLLMs. The image-based synthesis also allows us to focus on the specific-domain ability of MLLMs. Code and data will be publicly available.

Realistic hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on a kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact forces and finger torques. Consequently, these approaches prioritize tight, one-size-fits-all grips rather than reflecting users' intended force levels. We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions, faithfully reflecting the user's grip force intention. Instead of mimicking predefined motion datasets, ForceGrip uses generated training scenarios-randomizing object shapes, wrist movements, and trigger input flows-to challenge the agent with a broad spectrum of physical interactions. To effectively learn from these complex tasks, we employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization. This progressive strategy ensures stable hand-object contact, adaptive force control based on user inputs, and robust handling under dynamic conditions. Additionally, a proximity reward function enhances natural finger motions and accelerates training convergence. Quantitative and qualitative evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods. The video presentation of our paper is accessible at https://youtu.be/lR-YAfninJw.