technocracy

arXiv:2602.20213v1 Announce Type: new Abstract: The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass. To bridge this gap, we propose CodeHacker, an automated agent framework dedicated to generating targeted adversarial test cases that expose latent vulnerabilities in program submissions. Mimicking the hack mechanism in competitive programming, CodeHacker employs a multi-strategy approach, including […]

Ver mais

arXiv:2604.13204v1 Announce Type: new Abstract: The motion planning problem requires finding a collision-free path between start and goal configurations in high-dimensional, cluttered spaces. Recent learning-based methods offer promising solutions, with self-supervised physics-informed approaches such as Neural Time Fields (NTFields) solving the Eikonal equation to learn value functions without expert demonstrations. However, existing physics-informed methods struggle to scale in complex, multi-room environments, where simply increasing the number of samples cannot resolve local minima or guarantee global consistency. We propose […]

Ver mais

How a 180-year-old diagnosis explains what AI is doing to work, meaning, and identity in 2026 Part 5 of a six-part series using science fiction as a lens for understanding AI, work, and power in 2026. Work is about a search for daily meaning as well as daily bread. Studs Terkel, Working, 1974 Studs Terkel (an American writer and historian among other things) spent three years interviewing Americans about their jobs. What he found was a story about […]

Ver mais

arXiv:2508.01068v2 Announce Type: replace-cross Abstract: The equations of classical mechanics can be used to model the time evolution of countless physical systems, from the astrophysical to the atomic scale. Accurate numerical integration requires small time steps, which limits the computational efficiency — especially in cases such as molecular dynamics that span wildly different time scales. Using machine-learning (ML) algorithms to predict trajectories allows one to greatly extend the integration time step, at the cost of introducing artifacts such […]

Ver mais

Task sequencing (TS) is one of the core open problems in Deep Learning, arising in a plethora of real-world domains, from robotic assembly lines to autonomous driving. Unfortunately, prior work has not convincingly demonstrated the generalization ability of meta-learned TS methods to solve new TS problems, given few initial demonstrations. In this paper, we demonstrate that deep neural networks can meta-learn over an infinite prior of synthetically generated TS problems and achieve a few-shot generalization. We meta-learn a […]

Ver mais

Curriculum learning changes the order of pre-training data, but it remains unclear whether it changes the learning trajectory or mainly reorders exposure over a fixed trajectory. We train Pythia models (14M-410M parameters) for 300B tokens under three linguistically motivated curricula-Age-of-Acquisition, word frequency, and Verb Variation (VV)-and compare each against Random ordering; at 1B parameters we compare Random and VV. Across orderings, training follows a shared sequence of latent phases, while curricula mainly change within-phase data exposure. In smaller […]

Ver mais

arXiv:2603.26940v1 Announce Type: new Abstract: The optimal transportation problem defines a geometry of probability measures which leads to a definition for weighted averages (barycenters) of measures, finding application in the machine learning and computer vision communities as a signal processing tool. Here, we implement a barycentric coding model for measures which are supported on a graph, a context in which the classical optimal transport geometry becomes degenerate, by leveraging a Riemannian structure on the simplex induced by a […]

Ver mais