technocracy

arXiv:2603.08715v1 Announce Type: new Abstract: Rapid advances in language models (LMs) have created new opportunities for automated code generation while complicating trade-offs between model characteristics and prompt design choices. In this work, we provide an empirical map of recent trends in LMs for Verilog code generation, focusing on interactions among model reasoning, specialization, and prompt engineering strategies. We evaluate a diverse set of small and large LMs, including general-purpose, reasoning, and domain-specific variants. Our experiments use a controlled […]

Ver mais

arXiv:2602.15973v1 Announce Type: new Abstract: Neuromorphic engineering has a data problem. Despite the meteoric rise in the number of neuromorphic datasets published over the past ten years, the conclusion of a significant portion of neuromorphic research papers still states that there is a need for yet more data and even larger datasets. Whilst this need is driven in part by the sheer volume of data required by modern deep learning approaches, it is also fuelled by the current […]

Ver mais

The challenges of training and inference in few-shot environments persist in the area of graph representation learning. The quality and quantity of labels are often insufficient due to the extensive expert knowledge required to annotate graph data. In this context, Few-Shot Graph Learning (FSGL) approaches have been developed over the years. Through sophisticated neural architectures and customized training pipelines, these approaches enhance model adaptability to new label distributions. However, compromises in textcolor{black}{the model’s} robustness and interpretability can result […]

Ver mais

arXiv:2601.15331v1 Announce Type: new Abstract: The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common misuse, they remain vulnerable to automated jailbreaking methods such as GCG, PEZ, and GBDA, which generate adversarial suffixes via training and gradient-based search. Although effective, these methods particularly GCG are computationally expensive, limiting their practicality for organisations with constrained resources. This […]

Ver mais

Soft robotic grippers excel in unstructured manipulation but suffer catastrophic failure rates (72%) when grasping deformable organics, fabrics, and mixed debris due to hyperchaotic pneumatic dynamics. This paper introduces the first Lyapunov stability controller for soft robotics, deploying real-time maximal Lyapunov exponent estimation (λ_MLE) from fibre-optic strain sensor arrays running at 100Hz on Intel Loihi 2 neuromorphic chips. The system reconstructs 12D phase space embeddings via Takens theorem, detecting chaos onset 187ms early during dual-material transitions (tomato → […]

Ver mais

arXiv:2604.07427v1 Announce Type: new Abstract: Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for “average” human appeal, they fail to capture the inherent subjectivity of aesthetic judgment. In this work, we introduce a novel dataset and predictive framework, called PAMELA, designed to model personalized image evaluations. Our dataset comprises 70,000 ratings across 5,000 diverse images generated by state-of-the-art models (Flux 2 and Nano Banana). Each image is […]

Ver mais

arXiv:2603.24826v1 Announce Type: new Abstract: Synthetic data generation through document rewriting has emerged as a promising technique for improving language model pretraining, yet most studies focus on English and do not systematically control for the quality of the source data being rewritten. We present a controlled study of how synthetic rewriting interacts with source data quality in the context of Portuguese continued pretraining. Starting from ClassiCC-PT, a Portuguese corpus annotated with STEM and Educational quality scores, we construct […]

Ver mais

arXiv:2602.21249v1 Announce Type: new Abstract: Effective data processing depends on the quality of the underlying data. However, quality issues such as inconsistencies and uncertainties, can significantly impede the processing and subsequent use of data. Despite the centrality of data quality to a wide range of computational tasks, there is currently no broadly accepted, domain-independent consensus on the definition of data quality. Existing frameworks primarily define data quality in ways that are tailored to specific domains, data types, or […]

Ver mais

arXiv:2601.21324v1 Announce Type: new Abstract: Distributionally robust optimisation (DRO) minimises the worst-case expected loss over an ambiguity set that can capture distributional shifts in out-of-sample environments. While Huber (linear-vacuous) contamination is a classical minimal-assumption model for an $varepsilon$-fraction of arbitrary perturbations, including it in an ambiguity set can make the worst-case risk infinite and the DRO objective vacuous unless one imposes strong boundedness or support assumptions. We address these challenges by introducing bulk-calibrated credal ambiguity sets: we learn […]

Ver mais

arXiv:2602.04364v1 Announce Type: new Abstract: Prediction sets provide a means of quantifying the uncertainty in predictive tasks. Using held out calibration data, conformal prediction and risk control can produce prediction sets that exhibit statistically valid error control in a computationally efficient manner. However, in the standard formulations, the error is only controlled on average over many possible calibration datasets of fixed size. In this paper, we extend the control to remain valid with high probability over a cumulatively […]

Ver mais