arXiv:2601.15399v1 Announce Type: new Abstract: High-Performance Computing (HPC) schedulers must balance user performance with facility-wide resource constraints. The task boils down to selecting the optimal number of nodes for a given job. We present a surrogate-assisted multi-objective Bayesian optimization (MOBO) framework to automate this complex decision. Our core hypothesis is that surrogate models informed by attention-based embeddings of job telemetry can capture performance dynamics more effectively than standard regression techniques. We pair this with an intelligent sample acquisition […]

Ver mais

Hi everyone, I’ve recently finished re-engineering the Fuzzy-Pattern Tsetlin Machine (FPTM) from the ground up. My goal was to leverage low-level optimizations to see just how much throughput I could squeeze out of the architecture. The results are pretty wild. By focusing on cache locality and SIMD instructions, the new implementation is up to 10× faster in training and 34× faster in inference compared to the original FPTM. MNIST Benchmarks (Ryzen 7950X3D): ⚡ Throughput: 4 GB/s 🧠 Inference: […]

Ver mais

How are you, hacker? 🪐Want to know what’s trending right now?: The Techbeat by HackerNoon has got you covered with fresh content from our trending stories of the day! Set email preference here. ## What I’ve learned building an agent for Renovate config (as a cautious skeptic of AI) By @mend [ 9 Min read ] As an opportunity to “kick the tyres” of what agents are and how they work, I set aside a couple of hours […]

Ver mais

arXiv:2602.06049v1 Announce Type: new Abstract: Slogans are concise and memorable catchphrases that play a crucial role in advertising by conveying brand identity and shaping public perception. However, advertising fatigue reduces the effectiveness of repeated slogans, creating a growing demand for novel, creative, and insightful slogan generation. While recent work leverages large language models (LLMs) for this task, existing approaches often produce stylistically redundant outputs that lack a clear brand persona and appear overtly machine-generated. We argue that effective […]

Ver mais

arXiv:2601.05358v1 Announce Type: new Abstract: Public debates about “left-” or “right-wing” news overlook the fact that bias is usually conveyed by concrete linguistic manoeuvres that transcend any single political spectrum. We therefore shift the focus from where an outlet allegedly stands to how partiality is expressed in individual sentences. Drawing on 26,464 sentences collected from newsroom corpora, user submissions and our own browsing, we iteratively combine close-reading, interdisciplinary theory and pilot annotation to derive a fine-grained, sentence-level taxonomy […]

Ver mais

arXiv:2601.15294v1 Announce Type: new Abstract: Mathematical knowledge exists in many forms, ranging from informal textbooks and lecture notes to large formal proof libraries, yet moving between these representations remains difficult. Informal texts hide dependencies, while formal systems expose every detail in ways that are not always human-readable. Dependency graphs offer a middle ground by making visible the structure of results, definitions, and proofs. We present KnowTeX, a standalone, user-friendly tool that extends the ideas of Lean’s Blueprints, enabling […]

Ver mais

arXiv:2601.12343v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to predict human behavior. We propose a measure for evaluating how much knowledge a pretrained LLM brings to such a prediction: its equivalent sample size, defined as the amount of task-specific data needed to match the predictive accuracy of the LLM. We estimate this measure by comparing the prediction error of a fixed LLM in a given domain to that of flexible machine learning models trained […]

Ver mais

Sequential Bayesian optimal experimental design (SBOED) for PDE-governed inverse problems is computationally challenging, especially for infinite-dimensional random field parameters. High-fidelity approaches require repeated forward and adjoint PDE solves inside nested Bayesian inversion and design loops. We formulate SBOED as a finite-horizon Markov decision process and learn an amortized design policy via policy-gradient reinforcement learning (PGRL), enabling online design selection from the experiment history without repeatedly solving an SBOED optimization problem. To make policy training and reward evaluation scalable, […]

Ver mais