arXiv:2603.05630v1 Announce Type: new Abstract: It is well known that the reconstruction FID (rFID) of a VAE is poorly correlated with the generation FID (gFID) of a latent diffusion model. We propose interpolated FID (iFID), a simple variant of rFID that exhibits a strong correlation with gFID. Specifically, for each element in the dataset, we retrieve its nearest neighbor (NN) in the latent space and interpolate their latent representations. We then decode the interpolated latent and compute the […]

Ver mais

arXiv:2602.13297v1 Announce Type: new Abstract: High-resolution range profiles (HRRPs) enable fast onboard processing for radar automatic target recognition, but their strong sensitivity to acquisition conditions limits robustness across operational scenarios. Conditional HRRP generation can mitigate this issue, yet prior studies are constrained by small, highly specific datasets. We study HRRP synthesis on a largescale maritime database representative of coastal surveillance variability. Our analysis indicates that the fundamental scenario drivers are geometric: ship dimensions and the desired aspect angle. […]

Ver mais

With an emphasis on the distinct labor market structures of Africa and emerging markets, this paper offers a data-guided analysis of the effects of automation and artificial intelligence (AI) on the evolution of jobs. The study employs a mixed-methods approach and bases its conclusions on both detailed task-level data from the “Anthropic Economic Index” and a quantitative regression model of more than 1,000 occupations. The empirical findings show a strong negative correlation between automation probability and wages, meaning […]

Ver mais

Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space. Existing methods face notable limitations: GRPO samples exclusively from the root, saturating high-probability trajectories while leaving deep, error-prone states under-explored. Tree-based methods blindly disperse budgets across trivial or unrecoverable states, causing sampling dilution that fails to uncover rare correct suffixes and destabilizes local baselines. To address this, we propose Deep […]

Ver mais

arXiv:2602.04004v1 Announce Type: new Abstract: Understanding dataset semantics is crucial for effective search, discovery, and integration pipelines. To this end, column type annotation (CTA) methods associate columns of tabular datasets with semantic types that accurately describe their contents, using pre-trained deep learning models or Large Language Models (LLMs). However, existing approaches require users to specify a closed set of semantic types either at training or inference time, hindering their application to domain-specific datasets where pre-defined labels often lack […]

Ver mais

arXiv:2602.02523v1 Announce Type: new Abstract: Standard tabular benchmarks mainly focus on the evaluation of a model’s capability to interpolate values inside a data manifold, where models good at performing local statistical smoothing are rewarded. However, there exists a very large category of high-value tabular data, including financial modeling and physical simulations, which are generated based upon deterministic computational processes, as opposed to stochastic and noisy relationships. Therefore, we investigate if tabular models can provide an extension from statistical […]

Ver mais

In recent years, there has been growing interest in understanding neural architectures’ ability to learn to execute discrete algorithms, a line of work often referred to as neural algorithmic reasoning. The goal is to integrate algorithmic reasoning capabilities into larger neural pipelines. Many such architectures are based on (message-passing) graph neural networks (MPNNs), owing to their permutation equivariance and ability to deal with sparsity and variable-sized inputs. However, existing work is either largely empirical and lacks formal guarantees […]

Ver mais

How OpenAI built an agent runtime using the Responses API, shell tool, and hosted containers to run secure, scalable agents with files, tools, and state.

Ver mais

Accurate evaluation of extremely small Gaussian tail probabilities is essential in statistical meta-analyses, in which large z-scores (often exceeding 8 or 9) must be converted into p-values. Meanwhile, direct numerical integration of complementary error function erfc(a) suffers from severe underflow in floating-point arithmetic. In this paper, a simple and robust approximation scheme for log[erfc(a)] is proposed based on a geometric tangent construction. This approach yields explicit lower and upper bounds, closed-form asymptotic expansions up to order a^-8, and […]

Ver mais