arXiv preprints from January 1, 2026 through September 27, 2026 — 03:44:58 EST
We present a controlled study of how dataset contamination interacts with the post-training stages now standard in large language model training pipelines. Starting from clean checkpoints of Qwen2.5 (0.5B/1.5B) and Gemma3 (1B/4B), we inject five copies of GSM8K and MBPP test items into the first 2B tokens of an otherwise 25B token...
Language generation maps a rich, high-dimensional internal state to a single token sequence. We study this many-to-one mapping through the lens of intention collapse: the projection from an internal intention space I to an external language space L. We introduce three cheap, model-agnostic metrics computed on a pre-collapse state I:...
Prior research has shown that students' problem-solving pathways in game-based learning environments reflect their conceptual understanding, procedural knowledge, and flexibility. Replay behaviors, in particular, may indicate productive struggle or broader exploration, which in turn foster deeper learning. However, little is known...
Recent advances in artificial intelligence have produced systems capable of remarkable performance across a wide range of tasks. These gains, however, are increasingly accompanied by concerns regarding long-horizon developmental behavior, as many systems converge toward repetitive solution patterns rather than sustained growth. We...
This paper employs a data-driven approach to determine the impact of concrete mixture compositions on the temporal evolution of chloride in concrete structures. This is critical for assessing the service life of civil infrastructure subjected to aggressive environments. The adopted methodology relies on several simple and complex...
The widespread adoption of Artificial Intelligence (AI) in K-12 education highlights the need for psychometrically-tested measures of teachers' AI literacy. Existing work has primarily relied on either self-report (SR) or objective-based (OB) assessments, with few studies aligning the two within a shared framework to compare perceived...
Despite state-of-the-art vision-language models (VLMs) have demonstrated strong reasoning capabilities, their performance in multilingual mathematical reasoning remains underexplored, particularly when compared to human performance. To bridge this gap, we introduce M3Kang, the first massively multilingual, multimodal mathematical...
This paper, introducing a novel method in philomatics, draws on Wittgenstein's concept of family resemblance from analytic philosophy to develop a clustering algorithm for machine learning. According to Wittgenstein's Philosophical Investigations (1953), family resemblance holds that members of a concept or category are connected by...
We present RoboPhD, a system where AI agents autonomously conduct research to improve Text-to-SQL performance. RoboPhD implements a closed-loop evolution cycle with two coordinated components: a SQL Generation agent composed of a database analysis script and SQL generation instructions, and an Evolution agent that designs new versions...
The rapid proliferation of IoT applications has intensified the demand for efficient and secure service placement in Fog computing. However, heterogeneous resources, dynamic workloads, and diverse security requirements make optimal service placement highly challenging. Most solutions focus primarily on performance metrics while...
Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A crucial component of GNNs is the pooling procedure, in which the node features calculated by the model are combined to form an informative final descriptor to be used for the downstream task....
End-to-End Speech Translation often shows slower convergence and worse performance when target transcriptions exhibit high variance and semantic ambiguity. We propose Listen, Attend, Understand (LAU), a semantic regularization technique that constrains the acoustic encoder's latent space during training. By leveraging frozen text...
Early detection of chronic kidney disease (CKD) is essential for preventing progression to end-stage renal disease. However, existing screening tools - primarily developed using populations from high-income countries - often underperform in Bangladesh and South Asia, where risk profiles differ. Most of these tools rely on simple...
The rapid growth of AI for Science (AI4S) has underscored the significance of scientific datasets, leading to the establishment of numerous national scientific data centers and sharing platforms. Despite this progress, efficiently promoting dataset sharing and utilization for scientific research remains challenging. Scientific...
Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of alternatives -- Direct Preference Optimization (DPO), Identity Preference Optimization (IPO),...
We introduce EmoLoom-2B, a lightweight and reproducible pipeline that turns small language models under 2B parameters into fast screening candidates for joint emotion classification and Valence-Arousal-Dominance prediction. To ensure protocol-faithful and fair evaluation, we unify data loading, training, and inference under a single...
The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's capability of identifying high density regions in data distributions to purify adversarial...
Autonomous object recovery in the hadal zone is challenging due to extreme hydrostatic pressure, limited visibility and currents, and the need for precise manipulation at full ocean depth. Field experimentation in such environments is costly, high-risk, and constrained by limited vehicle availability, making early validation of...
We present HAQAGen, a unified generative model for resolution-invariant NIR-to-RGB colorization that balances chromatic realism with structural fidelity. The proposed model introduces (i) a combined loss term aligning the global color statistics through differentiable histogram matching, perceptual image quality measure, and feature...
Despite the rise of data-driven software systems in the modern digital landscape, data governance under a legal framework remains a critical challenge. In India, the Digital Personal Data Protection (DPDP) Act mandates rigorous data privacy and compliance requirements, necessitating software frameworks that are both ethical and...
This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary classification, fine-grained multiclass recognition, and object detection scenarios. We analyze how...
We propose a dedicated multimodal Judge Model designed to provide reliable, explainable evaluation across a diverse suite of tasks. Our benchmark spans text, audio, image, and video modalities, drawing from carefully sampled public datasets with fixed seeds to ensure reproducibility and minimize train test leakage. Instead of simple...
Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored. True narrative understanding requires grounding who is doing what, when, and where, maintaining coherent entity representations across...
Social cues, which convey others' presence, behaviors, or identities, play a crucial role in human information seeking by helping individuals judge relevance and trustworthiness. However, existing LLM-based search systems primarily rely on semantic features, creating a misalignment with the socialized cognition underlying natural...
Large Language Models (LLMs) demonstrate remarkable fluency across high-resource languages yet consistently fail to generate coherent text in Kashmiri, a language spoken by approximately seven million people. This performance disparity stems not from inherent model limitations but from a critical scarcity of high-quality training...