arXiv:2510.27212v1 Announce Type: cross Abstract: The remarkable progress of artificial intelligence (AI) has revealed the enormous energy demands of modern digital architectures, raising deep concerns about sustainability. In stark contrast, the human brain operates efficiently on only ~20 watts, and individual cells process gigabit-scale genetic information using energy on the order of trillionths of a […]
Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
arXiv:2509.15981v2 Announce Type: replace-cross Abstract: In reinforcement learning with sparse rewards, demonstrations can accelerate learning, but determining when to imitate them remains challenging. We propose Smooth Policy Regularisation from Demonstrations (SPReD), a framework that addresses the fundamental question: when should an agent imitate a demonstration versus follow its own policy? SPReD uses ensemble methods to […]
Vintage Code, Modern Judges: Meta-Validation in Low Data Regimes
arXiv:2510.27244v1 Announce Type: cross Abstract: Application modernization in legacy languages such as COBOL, PL/I, and REXX faces an acute shortage of resources, both in expert availability and in high-quality human evaluation data. While Large Language Models as a Judge (LaaJ) offer a scalable alternative to expert review, their reliability must be validated before being trusted […]
From product to system network challenges in system of systems lifecycle management
arXiv:2510.27194v1 Announce Type: new Abstract: Today, products are no longer isolated artifacts, but nodes in networked systems. This means that traditional, linearly conceived life cycle models are reaching their limits: Interoperability across disciplines, variant and configuration management, traceability, and governance across organizational boundaries are becoming key factors. This collective contribution classifies the state of the […]
Languages are Modalities: Cross-Lingual Alignment via Encoder Injection
arXiv:2510.27254v1 Announce Type: cross Abstract: Instruction-tuned Large Language Models (LLMs) underperform on low resource, non-Latin scripts due to tokenizer fragmentation and weak cross-lingual coupling. We present LLINK (Latent Language Injection for Non-English Knowledge), a compute efficient language-as-modality method that conditions an instruction-tuned decoder without changing the tokenizer or retraining the decoder. First, we align sentence […]
DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications
arXiv:2510.25140v2 Announce Type: replace-cross Abstract: Object detection in civil engineering applications is constrained by limited annotated data in specialized domains. We introduce DINO-YOLO, a hybrid architecture combining YOLOv12 with DINOv3 self-supervised vision transformers for data-efficient detection. DINOv3 features are strategically integrated at two locations: input preprocessing (P0) and mid-backbone enhancement (P3). Experimental validation demonstrates substantial […]
Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
arXiv:2510.27269v1 Announce Type: cross Abstract: Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still suffer from a multilingual reasoning gap, performing better in high-resource languages than in low-resource ones. While recent efforts have reduced this gap, its underlying causes remain largely unexplored. In this paper, we address this by showing […]
Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering
arXiv:2510.27206v1 Announce Type: new Abstract: The rapid evolution of large language models (LLMs) has intensified the demand for effective personalization techniques that can adapt model behavior to individual user preferences. Despite the non-parametric methods utilizing the in-context learning ability of LLMs, recent parametric adaptation methods, including personalized parameter-efficient fine-tuning and reward modeling emerge. However, these […]
Un-Attributability: Computing Novelty From Retrieval & Semantic Similarity
arXiv:2510.27313v1 Announce Type: cross Abstract: Understanding how language-model outputs relate to the pretraining corpus is central to studying model behavior. Most training data attribution (TDA) methods ask which training examples causally influence a given output, often using leave-one-out tests. We invert the question: which outputs cannot be attributed to any pretraining example? We introduce un-attributability […]
CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
arXiv:2510.27442v1 Announce Type: cross Abstract: Vision Transformers (ViTs) have demonstrated strong potential in medical imaging; however, their high computational demands and tendency to overfit on small datasets limit their applicability in real-world clinical scenarios. In this paper, we present CoMViT, a compact and generalizable Vision Transformer architecture optimized for resource-constrained medical image analysis. CoMViT integrates […]