Recent advances in large language models (LLMs) have enabled natural language interfaces that translate user questions into database queries, such as Text2SQL, Text2SPARQL, and Text2Cypher. While these interfaces enhance database accessibility, most research today focuses on English, with limited evaluation in other languages. This paper investigates the performance of both foundational and finetuned LLMs on the Text2Cypher task across multiple languages. We create and release a multilingual dataset by translating English questions into Spanish and Turkish while preserving the original Cypher queries, enabling fair cross-lingual comparison. Using standardized prompts and metrics, we evaluate several foundational models and observe a consistent performance pattern: highest on English, followed by Spanish, and lowest on Turkish. We attribute this to differences in training data availability and linguistic features. We also examine the impact of translating task prompts into Spanish and Turkish. Results show little to no change in evaluation metrics, suggesting prompt translation has minor impact. Furthermore, we finetune a foundational model on two datasets: one in English only, and one multilingual. Finetuning on English improves overall accuracy but widens the performance gap between languages. In contrast, multilingual finetuning narrows the gap, resulting in more balanced performance. Our findings highlight the importance for multilingual evaluation and training to build more inclusive and robust query generation systems.

Instead of relying on acoustic signals, SSIs exploit non-vocal modalities that capture articulatory and physiological activity underlying speech production. A variety of input sources have been investigated, including surface electromyography (EMG), ultrasound tongue imaging (UTI), electromagnetic articulography (EMA), and visual cues from lip movements. These modalities offer complementary perspectives on articulatory dynamics, positioning SSIs as a promising solution for communication in scenarios where acoustic speech is impaired. Recent advances in SSI have introduced convolutionaltransducer models combined with transformer encoders and auxiliary phoneme prediction losses, achieving notable improvements in intelligibility. The input signals typically undergo feature extraction to capture articulatory or physiological attributes that preserve discriminative information necessary for speech generation.

Large language models (LLMs) learn non-trivial abstractions during pretraining, like detecting irregular plural noun subjects. However, it is not well understood when and how specific linguistic abilities emerge as traditional evaluation methods such as benchmarking fail to reveal how models acquire concepts and capabilities. To bridge this gap and better understand model training at the concept level, we use sparse crosscoders to discover and align features across model checkpoints. Using this approach, we track the evolution of linguistic features during pretraining. We train crosscoders between open-sourced checkpoint triplets with significant performance and representation shifts, and introduce a novel metric, Relative Indirect Effects (RelIE), to trace training stages at which individual features become causally important for task performance. We show that crosscoders can detect feature emergence, maintenance, and discontinuation during pretraining. Our approach is architecture-agnostic and scalable, offering a promising path toward more interpretable and fine-grained analysis of representation learning throughout pretraining.

Chain-of-thought reasoning, while powerful, can produce unnecessarily verbose output for simpler problems. We present a framework for difficulty-aware reasoning that teaches models to dynamically adjust reasoning depth based on problem complexity. Remarkably, we show that models can be endowed with such dynamic inference pathways without any architectural modifications; we simply post-train on data that is carefully curated to include chain-of-thought traces that are proportional in length to problem difficulty. Our analysis reveals that post-training via supervised fine-tuning (SFT) primarily captures patterns like reasoning length and format, while direct preference optimization (DPO) preserves reasoning accuracy, with their combination reducing length and maintaining or improving performance. Both quantitative metrics and qualitative assessments confirm that models can learn to "think proportionally", reasoning minimally on simple problems while maintaining depth for complex ones.

Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored. We study symbolic graphics programming, where the goal is to generate an SGP from a natural-language description. This task also serves as a lens into how LLMs understand the visual world by prompting them to generate images rendered from SGPs. Among various SGPs, our paper sticks to scalable vector graphics (SVGs). We begin by examining the extent to which LLMs can generate SGPs. To this end, we introduce SGP-GenBench, a comprehensive benchmark covering object fidelity, scene fidelity, and compositionality (attribute binding, spatial relations, numeracy). On SGP-GenBench, we discover that frontier proprietary models substantially outperform open-source models, and performance correlates well with general coding capabilities. Motivated by this gap, we aim to improve LLMs' ability to generate SGPs. We propose a reinforcement learning (RL) with verifiable rewards approach, where a format-validity gate ensures renderable SVG, and a cross-modal reward aligns text and the rendered image via strong vision encoders (e.g., SigLIP for text-image and DINO for image-image). Applied to Qwen-2.5-7B, our method substantially improves SVG generation quality and semantics, achieving performance on par with frontier systems. We further analyze training dynamics, showing that RL induces (i) finer decomposition of objects into controllable primitives and (ii) contextual details that improve scene coherence. Our results demonstrate that symbolic graphics programming offers a precise and interpretable lens on cross-modal grounding.

Large Language Models (LLMs) such as GPT -5, GEMINI, Claude, and LLaMA have become foundational tools in artificial intelligence (AI), achieving state-of-the-art performance in summarization, translation, reasoning, and dialogue. However, since LLMs are increasingly integrated in high-risk decision making in domains such as healthcare, law, and education, their lack of transparency raises urgent concerns for safety, accountability, and public trust [12]. The scale and complexity of these models, covering billions of parameters trained in opaque corpora, make their internal reasoning fundamentally inscrutable. This opacity creates barriers to responsible adoption, as users often lack meaningful ways to understand or challenge outputs. Without stakeholder-sensitive explanations, systems risk overtrust, misinterpretation, or outright rejection [11]. Explainable AI (XAI) for LLMs has therefore evolved beyond technical introspection [6]. The goal is not only to expose internal mechanisms but also to support human interaction, trust calibration, and decision assurance. As model behavior becomes more emergent and unpredictable [10], explanation systems must serve cognitive, functional, and ethical purposes simultaneously [7].

Automated web testing plays a critical role in ensuring high-quality user experiences and delivering business value. Traditional approaches primarily focus on code coverage and load testing, but often fall short of capturing complex user behaviors, leaving many usability issues undetected. The emergence of large language models (LLM) and AI agents opens new possibilities for web testing by enabling human-like interaction with websites and a general awareness of common usability problems. In this work, we present WebProber, a prototype AI agent-based web testing framework. Given a URL, WebProber autonomously explores the website, simulating real user interactions, identifying bugs and usability issues, and producing a human-readable report. We evaluate WebProber through a case study of 120 academic personal websites, where it uncovered 29 usability issues--many of which were missed by traditional tools. Our findings highlight agent-based testing as a promising direction while outlining directions for developing next-generation, user-centered testing frameworks.

--Shared autonomy is a promising paradigm in robotic systems, particularly within the maritime domain, where complex, high-risk, and uncertain environments necessitate effective human-robot collaboration. This paper investigates the interaction of three complementary approaches to advance shared autonomy in heterogeneous marine robotic fleets: (i) the integration of Large Language Models (LLMs) to facilitate intuitive high-level task specification and support hull inspection missions, (ii) the implementation of human-in-the-loop interaction frameworks in multi-agent settings to enable adaptive and intent-aware coordination, and (iii) the development of a modular Mission Manager based on Behavior Trees to provide interpretable and flexible mission control. Preliminary results from simulation and real-world lake-like environments demonstrate the potential of this multi-layered architecture to reduce operator cognitive load, enhance transparency, and improve adaptive behaviour alignment with human intent. Ongoing work focuses on fully integrating these components, refining coordination mechanisms, and validating the system in operational port scenarios. This study contributes to establishing a modular and scalable foundation for trustworthy, human-collaborative autonomy in safety-critical maritime robotics applications.

In the era of conversational AI, generating accurate and contextually appropriate service responses remains a critical challenge. A central question remains: Is explicit intent recognition a prerequisite for generating high-quality service responses, or can models bypass this step and produce effective replies directly? This paper conducts a rigorous comparative study to address this fundamental design dilemma. Leveraging two publicly available service interaction datasets, we benchmark several state-of-the-art language models, including a fine-tuned T5 variant, across both paradigms: Intent-First Response Generation and Direct Response Generation. Evaluation metrics encompass both linguistic quality and task success rates, revealing surprising insights into the necessity or redundancy of explicit intent modelling. Our findings challenge conventional assumptions in conversational AI pipelines, offering actionable guidelines for designing more efficient and effective response generation systems.

Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by the limited context in short texts. These factors make it difficult to resolve ambiguity and exacerbate data sparsity, hindering effective learning. In this paper, we evaluate the effectiveness of small Transformer-based models (i.e., BERT and RoBERTa, with fewer than 1 billion parameters) for multi-label sentiment classification, with a particular focus on short-text settings. Specifically, we evaluated three key factors influencing model performance: (1) continued domain-specific pre-training, (2) data augmentation using automatically generated examples, specifically generative data augmentation, and (3) architectural variations of the classification head. Our experiment results show that data augmentation improves classification performance, while continued pre-training on augmented datasets can introduce noise rather than boost accuracy. Furthermore, we confirm that modifications to the classification head yield only marginal benefits. These findings provide practical guidance for optimizing BERT-based models in resource-constrained settings and refining strategies for sentiment classification in short-text datasets.