technocracy

arXiv:2306.12344v3 Announce Type: replace-cross Abstract: Algorithms for solving the linear classification problem have a long history, dating back at least to 1936 with linear discriminant analysis. For linearly separable data, many algorithms can obtain the exact solution to the corresponding 0-1 loss classification problem efficiently, but for data which is not linearly separable, it has been shown that this problem, in full generality, is NP-hard. Alternative approaches all involve approximations of some kind, such as the use of […]

Ver mais

Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators with varying reliability; some accurate, some noisy, and some systematically adversarial. Existing PBRL methods either treat all feedback equally or attempt to filter out unreliable sources, but both approaches fail when faced with adversarial annotators who systematically provide incorrect preferences. We introduce TriTrust-PBRL (TTP), a unified framework that jointly learns a […]

Ver mais

Claude can code, but can it check binary executables? We already did our experiments with using NSA software to hack a classic Atari game. This time, we want to focus on a much more practical task — using AI agents for malware detection. We partnered with Michał “Redford” Kowalczyk,a reverse engineering expert from Dragon Sector, known for finding malicious code in Polish trains, to create a benchmark of finding backdoors in binary executables, without access to source code. […]

Ver mais

arXiv:2602.12351v1 Announce Type: new Abstract: This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VLA) models for long-horizon navigation. Unlike existing single-turn paradigm, LongNav-R1 reformulates the navigation decision process as a continuous multi-turn conversation between the VLA policy and the embodied environment. This multi-turn RL framework offers two distinct advantages: i) it enables the agent to reason about the causal effects of historical interactions and sequential future outcomes; and ii) it allows […]

Ver mais

arXiv:2601.17009v1 Announce Type: new Abstract: Drones are becoming more and more popular nowadays. They are small in size, low in cost, and reliable in operation. They contain a variety of sensors and can perform a variety of flight tasks, reaching places that are difficult or inaccessible for humans. Earthquakes damage a lot of infrastructure, making it impossible for rescuers to reach some areas. But drones can help. Many amateur and professional photographers like to use drones for aerial […]

Ver mais

arXiv:2601.14260v1 Announce Type: new Abstract: Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent movement of intermediate results between memory and compute units, leading to high latency and energy costs. Second, in long-context inference, the key-value cache (KV cache) can grow unpredictably and even surpass the model’s weight size, creating severe memory and bandwidth bottlenecks. Third, […]

Ver mais

arXiv:2601.14320v1 Announce Type: new Abstract: This work presents two integration methods for field transfer in computational aeroacoustics and in coupled field problems, using the finite element method to solve the acoustic field. Firstly, a high-order Gaussian quadrature computes the finite element right-hand side. In contrast, the (flow) field provided by the finite difference mesh is mapped by higher-order B-Splines or a Lagrangian function. Secondly, the cut-cell or supermesh integration with geometric clipping. For each method, the accuracy, performance […]

Ver mais

arXiv:2504.02627v2 Announce Type: replace-cross Abstract: Markov chain Monte Carlo (MCMC) methods are a powerful but computationally expensive way of performing non-parametric Bayesian inference. MCMC proposals which utilise gradients, such as Hamiltonian Monte Carlo (HMC), can better explore the parameter space of interest if the additional hyper-parameters are chosen well. The No-U-Turn Sampler (NUTS) is a variant of HMC which is extremely effective at selecting these hyper-parameters but is slow to run and is not suited to GPU architectures. […]

Ver mais

arXiv:2603.18736v1 Announce Type: cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling heavily relies on experimental feedback data collected from human annotators under controlled and costly conditions. In this work, we introduce observational reward modeling — learning reward models with observational user feedback (e.g., clicks, copies, and upvotes) — as a scalable and cost-effective alternative. We identify two fundamental challenges in this setting: (1) observational feedback is noisy […]

Ver mais

arXiv:2603.06726v1 Announce Type: new Abstract: Electricity market prices exhibit extreme volatility, nonlinearity, and non-stationarity, making accurate forecasting a significant challenge. While cutting-edge time series foundation models (TSFMs) effectively capture temporal dependencies, they typically underutilize cross-variate correlations and non-periodic patterns that are essential for price forecasting. Conversely, regression models excel at capturing feature interactions but are limited to future-available inputs, ignoring crucial historical drivers that are unavailable at forecast time. To bridge this gap, we propose FutureBoosting, a novel […]

Ver mais