digitado

arXiv:2603.23646v1 Announce Type: new Abstract: While recent work has benchmarked large language models on Swiss legal translation (Niklaus et al., 2025) and academic legal reasoning from university exams (Fan et al., 2025), no existing benchmark evaluates frontier model performance on applied Swiss regulatory compliance tasks. I introduce Swiss-Bench SBP-002, a trilingual benchmark of 395 expert-crafted items spanning three Swiss regulatory domains (FINMA, Legal-CH, EFK), seven task types, and three languages (German, French, Italian), and evaluate ten frontier models […]

Ver mais

arXiv:2603.23640v1 Announce Type: new Abstract: Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope, and memory. We benchmark Qwen 2.5 1.5B (4-bit quantised) across four platforms: a Raspberry Pi 5 with Hailo-10H NPU, a Samsung Galaxy S24 Ultra, an iPhone 16 Pro, and a laptop NVIDIA RTX 4050 GPU. Using a fixed 258-token prompt over 20 warm-condition iterations per device, we measure throughput, latency, power, and thermal […]

Ver mais

arXiv:2603.23639v1 Announce Type: new Abstract: We contribute two design studies for augmented reality visualizations that support learning musical instruments. First, we designed simple, glanceable encodings for drum kits, which we display through a projector. As second instrument, we chose guitar and designed visualizations to be displayed either on a screen as an augmented mirror or as an optical see-through AR headset. These modalities allow us to also show information around the instrument and in 3D. We evaluated our […]

Ver mais

arXiv:2603.23638v1 Announce Type: new Abstract: Large language models (LLMs) have enabled agentic systems that can reason, plan, and act across complex tasks, but it remains unclear whether they can allocate resources effectively under uncertainty. Unlike short-horizon reactive decisions, allocation requires committing scarce resources over time while balancing competing objectives and preserving flexibility for future needs. We introduce EnterpriseArena, the first benchmark for evaluating agents on long-horizon enterprise resource allocation. It instantiates CFO-style decision-making in a 132-month enterprise simulator […]

Ver mais

arXiv:2603.23637v1 Announce Type: new Abstract: Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization — rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction — but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises. We present a differentiable, sorting-free stochastic formulation for ray-traced […]

Ver mais

arXiv:2603.23633v1 Announce Type: new Abstract: Large language models can generate runnable software artifacts, but their security remains difficult to evaluate end to end. This study examines that problem through a Detect–Repair–Verify (DRV) workflow, in which vulnerabilities are detected, repaired, and then rechecked with security and functional tests. It addresses four gaps in current evidence: the lack of test-grounded benchmarks for LLM-generated artifacts, limited evidence on pipeline-level effectiveness, unclear reliability of detection reports as repair guidance, and uncertain repair […]

Ver mais

arXiv:2603.23631v1 Announce Type: new Abstract: Musicians mostly have to rely on their ears when they want to analyze what they play, for example to detect errors. Since hearing is sequential, it is not possible to quickly grasp an overview over one or multiple recordings of a whole piece of music at once. We therefore propose various visualizations that allow analyzing errors and stylistic variance. Our current approach focuses on rhythm and uses MIDI data for simplicity.

Ver mais

arXiv:2603.23629v1 Announce Type: new Abstract: Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at inference time. Using a difference-in-means method, we estimate layer-wise steering vectors for five language/library pairs and add them to model hidden states during generation. Across three open-weight code LLMs, these interventions substantially increase generation toward the target ecosystem under neutral prompts […]

Ver mais

arXiv:2603.23627v1 Announce Type: new Abstract: This study presents a benchmark for evaluating the Visual Word Sense Disambiguation (Visual-WSD) task in Ukrainian. The main goal of the Visual-WSD task is to identify, with minimal contextual information, the most appropriate representation of a given ambiguous word from a set of ten images. To construct this benchmark, we followed a methodology similar to that proposed by (CITATION), who previously introduced benchmarks for the Visual-WSD task in English, Italian, and Farsi. This […]

Ver mais

arXiv:2603.23626v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fundamental limits of such LLM-mediated improvement remain poorly understood. Here we propose a theory of LLM information susceptibility, centred on the hypothesis that when computational resources are sufficiently large, the intervention of a fixed LLM does not increase the performance susceptibility of a strategy set with respect to budget. We develop a multi-variable utility-function framework that generalizes this […]

Ver mais