News & Research

arXiv:2603.26906v2 Announce Type: replace Abstract: Secondary school students increasingly encounter AI systems whose outputs depend on data quality, evaluation choices and modeling assumptions. To provide accessible entry points to these interconnected concepts, we developed KI-Adventskalender, a free web-based extracurricular initiative with 24 didactically curated, short, guided micro-challenges released daily in December, targeting data-centric competencies and socio-technical themes that shape how data are interpreted in practice. Drawing on two annual iterations, we report aggregate platform traces characterizing participation and task-level engagement. Participation increased substantially in 2025, but early attrition persists. Progression stabilized after midpoint: among users reaching Day 12 in 2025, more than 75% completed the calendar. Competence cluster performance shifted across years; higher revision rates co-occurred with strong pass rates, suggesting sustained engagemen

arXiv:2605.06307v2 Announce Type: replace Abstract: Student simulation with Large language models (LLMs) offers a scalable alternative for educational research and teacher training. Yet, its validity depends on whether models maintain stable personas across extended interactions. We test this prerequisite using a dual-assessment framework measuring self-reported characteristics and observer-rated behavioral expressions. Across two experiments testing four clinically-grounded ADHD persona conditions, five LLMs, and three prompt designs, we quantify between-conversation stability (N=4,968) and within-conversation stability (N=3,952 across 9 turns). Self-reported characteristics remain stable for high intensities, constituting a necessary prerequisite for valid behavioral simulation. Observer-rated behavioral expression reveals selective instability: within-conversation drift occurs in unscripted dialog for high and moderate ADHD personas. Scripted interactions with explicit task prompts

arXiv:2605.07018v2 Announce Type: replace Abstract: Social media is central to how young people maintain relationships, develop identity, and access communities, yet dominant platform designs often leave youth feeling disempowered rather than supported. My dissertation argues that youth social media design is shaped by three forms of problem-space misattunement. \textit{Conceptual misattunement} occurs when the language of ``social media'' anchors participants to existing platforms' interaction templates. I address this through a Fictional Inquiry design workshop that frees youth from preconceived notions of social media by having them brainstorm ways to ``magically connect with remote wizard friends'' rather than ideas for ``social media.'' \textit{Definitional misattunement} occurs when researchers define what ``better'' means on youth's behalf. I address this through a Discord-based asynchronous community that supports youth-led collective inquiry. \textit{Evaluative misattunement}

arXiv:2605.07025v2 Announce Type: replace Abstract: We present a design framework for friendship-supportive youth social media, derived from a synthesis of five empirical studies with 331 youth participants (ages 13-25) using interviews, co-design, surveys, diary studies, and a field deployment. Iterative analysis of 209 design-relevant data points identified three pillars: Social Understanding (interaction norms, interaction cues and scaffolding, social accountability and governance), Placeness (third place and community, boundaries and personal spaces, shared presence), and Identity Alignment (identity currency, identity plurality, relational identity signals). The framework maps nine design spaces through which platforms can support the conditions under which youth friendships form, deepen, and are maintained. It offers a shared vocabulary for locating contributions, comparing design interventions, and identifying under-explored areas for future work.

arXiv:2605.11562v2 Announce Type: replace Abstract: Background: Stress has become a widespread phenomenon, and serious games are increasingly recognized as engaging tools for stress relief. However, despite the rapid advancement of Generative Artificial Intelligence (Gen-AI), its integration into stress-relief serious games remains insufficiently explored. Objective: This study aimed to address this gap by developing "Reverie", an Gen-AI driven serious game powered by the Unity engine and ChatGPT, and to preliminarily evaluate its effectiveness in stress reduction, user experience, and cognitive emotion regulation. Methods: A 14-day pilot study was conducted with 20 students experiencing moderate to high levels of stress. Participants used "Reverie" as a stress-relief intervention. Stress levels, user experience, and cognitive emotion regulation strategies were assessed to examine the game's feasibility and preliminary efficacy. Results: The results showed that "Reverie" significantly

arXiv:2605.22894v2 Announce Type: replace-cross Abstract: Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents actions, physical states, and text as dedicated token streams and couples them through joint attention, enabling direct interaction between language semantics and control dynamics. To stabilize autoregressive control, we introduce a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly

arXiv:2605.23904v2 Announce Type: replace Abstract: Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three ex

arXiv:2406.09250v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a robust and model-agnostic detection framework that operates effectively in both unimodal and multimodal settings. MirrorCheck leverages Text-to-Image (T2I) models to regenerate visual content from captions produced by the target model and assesses semantic consistency by comparing feature-space embeddings between the original and synthesized images. To enhance robustness against adaptive attacks, MirrorCheck introduces a stochastic defense strategy that randomly selects T2I generators and image encoders from a diverse model zoo. Additionally, we incorporate a novel One-Time-Use (OTU) perturbation applied to the selected encoder embeddings, regulated by a scaling factor, which decreases the effectiv

arXiv:2512.12677v3 Announce Type: replace-cross Abstract: We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained causal LLM and fine-tuning it on the task, using the LLM's final-token embedding as a sequence representation, and (2) instruction-tuning the LLM in a prompt-to-response format for classification. To enable single-GPU fine-tuning of models up to 8B parameters, we combine 4-bit model quantization with Low-Rank Adaptation (LoRA) for parameter-efficient training. Experiments on two patent benchmarks, a 5-class single-label internal corpus and the public WIPO-Alpha multi-label dataset with 14 categories, show that the embedding-head approach matches or exceeds fine-tuned BERT baselines on single-label classification while training 10-30x fewer parameters. Instruction-tuning is competitive only in the m

arXiv:2602.20210v3 Announce Type: replace-cross Abstract: Crystal modeling spans a family of conditional and unconditional generation tasks, including crystal structure prediction (CSP) and de novo generation (DNG). While recent deep generative models have shown promising performance, they remain largely task-specific, lacking a unified framework that shares crystal representations across tasks. To address this limitation, we propose Multimodal Crystal Flow (MCFlow), a unified multimodal flow model that realizes multiple crystal generation tasks as distinct inference trajectories via independent time variables for atom types and crystal structures. To enable multimodal flow in a standard transformer model, we introduce a composition- and symmetry-aware atom ordering with hierarchical permutation augmentation, injecting compositional and crystallographic priors without explicit structural templates. Experiments on the MP-20 and MPTS-52 benchmarks show that a single MCFlow model is compe

arXiv:2605.23082v2 Announce Type: replace-cross Abstract: Survival analysis aims to model how covariates and time jointly shape the time-to-event distribution under right censoring. Classical methods such as the Cox model and generalised additive models (GAMs) require interactions and time-varying effects to be manually specified, which is increasingly impractical on rich clinical datasets. We introduce KAPLAN-HR, a B-spline Kolmogorov-Arnold Network (KAN) for nonparametric estimation of the conditional hazard as a joint function of covariates and time. A single-layer KAPLAN-HR model recovers a GAM, while deeper architectures capture interactions and time-varying effects through composition. We establish a convergence rate for the nonparametric KAN hazard estimator that depends only on the smoothness of the underlying KAN representation and not on the covariate dimension, thereby mitigating the curse of dimensionality for KAN-representable targets. In evaluations over six clinical benc

arXiv:2605.23473v2 Announce Type: replace-cross Abstract: Bayesian optimization is widely employed for optimizing complex black-box functions but struggles with the curse of dimensionality. Random embedding, as a dimension reduction strategy, simplifies tasks that possess the effective dimension by optimizing within a low-dimensional subspace. However, determining the effective dimension of a task in advance remains a significant challenge, which influences the selection of the subspace dimensionality and the optimization performance. Traditional methods use fixed subspace dimensions provided by experts or rely on trial and error to estimate subspace dimensions with resources consumed. To this end, this paper proposes an automated random embedding for high-dimensional Bayesian optimization with unknown effective dimension, called Dynamic Shared Embedding Bayesian Optimization (DSEBO). DSEBO starts with a low dimension and switches to a higher subspace if the solutions in the current su

arXiv:2605.23491v2 Announce Type: replace-cross Abstract: Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signa

arXiv:2605.22903v1 Announce Type: new Abstract: Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly reflect reliance on visual evidence. Motivated by a surprising observation that removing a substantial fraction of image tokens only degrades model performance very slightly on a widely used hallucination benchmark, we systematically investigate this mismatch in a set of open-source VLMs. Our analysis spans multiple levels of granularity, spanning global visual degradation, localized occlusion, question reformulation, answer-space expansion, and decision-level analyses beyond standard accuracy. We further complement these behavioral results with a layer-wise analysis of vision-token geometry. Throughout the experiments, we find that although VLMs do incorporate visual input, their predictions are less sensitive to the loss of fine-grained visual evidence that stan

arXiv:2605.22907v1 Announce Type: new Abstract: Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal spans within extreme video durations. Mastering this intense cognitive load constitutes the fundamental bottleneck in long video understanding. While existing benchmarks have driven progress by scaling up video duration, their evaluation tasks often require comprehending only short and isolated video segments, falling short of capturing the challenge of ultra-long-context reasoning. To measure this cognitive load, we emphasize continuous certificate length, defined as the video length a human must continuously watch to definitively answer a given question. Driven by this metric, we introduce VideoOdyssey, a benchmark specifically designed for ultra-long-context and omni-modal video understanding. VideoOdyssey is characterized by three key features: 1) Extreme video duration and diversity: s