Active learning (AL) aims to reduce annotation costs while maximizing model performance by iteratively selecting valuable instances. While foundation models have made it easier to identify these instances, existing selection strategies still lack robustness across different models, annotation budgets, and datasets. To highlight the potential weaknesses of existing AL strategies and provide a reference point for research, we explore oracle strategies, i.e., strategies that approximate the optimal selection by accessing ground-truth information unavailable in practical AL scenarios. Current […]

Ver mais

The landscape of extremely low-resource machine translation (MT) is characterized by perplexing variability in reported performance, often making results across different language pairs difficult to contextualize. For researchers focused on specific language groups — such as ancient languages — it is nearly impossible to determine if breakthroughs reported in other contexts (e.g., native African or American languages) result from superior methodologies or are merely artifacts of benchmark collection. To address this problem, we introduce the FRED Difficulty Metrics, […]

Ver mais

arXiv:2602.11209v1 Announce Type: new Abstract: While AI-coding assistants accelerate software development, current testing frameworks struggle to keep pace with the resulting volume of AI-generated code. Traditional fuzzing techniques often allocate resources uniformly and lack semantic awareness of algorithmic vulnerability patterns, leading to inefficient resource usage and missed vulnerabilities. To address these limitations, we present a hybrid testing framework that leverages LLM-guided adaptive fuzzing to detect algorithmic vulnerabilities efficiently. Our system SAFuzz integrates prompt-based behavioral diversification, harness generation with […]

Ver mais

arXiv:2603.28324v1 Announce Type: new Abstract: We introduce a novel conditional stochastic interpolant framework for generative modeling of three-dimensional shapes. The method builds on a recent LDDMM-based registration approach to learn the conditional drift between geometries. By leveraging the resulting pull-back and push-forward operators, we extend this formulation beyond standard Cartesian grids to complex shapes and random variables defined on distinct domains. We present an application in the context of cardiovascular simulations, where aortic shapes are generated from an […]

Ver mais

Hey, I’ve been going down the rabbit hole of sim-to-real RL and I’m trying to understand where the ACTUAL bottlenecks are for people doing this in practice (not just in papers). From what I’ve read, domain randomization and system identification help close the gap, but it seems like there’s still a lot of pain around rare/adversarial scenarios that you can’t really plan for in sim. For those of you actually deploying RL policies on physical robots: What part […]

Ver mais

arXiv:2602.11159v1 Announce Type: new Abstract: The increasing use of Machine Learning (ML) in sensitive domains such as healthcare, finance, and public policy has raised concerns about the transparency of automated decisions. Explainable AI (XAI) addresses this by clarifying how models generate predictions, yet most methods demand technical expertise, limiting their value for novices. This gap is especially critical in no-code ML platforms, which seek to democratize AI but rarely include explainability. We present a human-centered XAI module in […]

Ver mais

arXiv:2601.04301v1 Announce Type: new Abstract: As frontier AI systems are pretrained on web-scale data, test set contamination has become a critical concern for accurately assessing their capabilities. While research has thoroughly investigated the impact of test set contamination on discriminative evaluations like multiple-choice question-answering, comparatively little research has studied the impact of test set contamination on generative evaluations. In this work, we quantitatively assess the effect of test set contamination on generative evaluations through the language model lifecycle. […]

Ver mais

arXiv:2601.07841v1 Announce Type: new Abstract: NTRU is one of the important lattice-based post-quantum cryptography methods, offering resistance against quantum computing attacks. However, a drawback of NTRU lies in its relatively low efficiency in generating key pairs. Therefore, this study proposes an NTRU-based key expansion method that enables efficient public key expansion. Furthermore, the proposed method is applied to an anonymous certificate scheme, allowing an end entity to generate a key pair only once, after which the certificate authority […]

Ver mais

arXiv:2507.05064v3 Announce Type: replace Abstract: Gaussian processes are flexible, probabilistic, non-parametric models widely used in machine learning and statistics. However, their scalability to large data sets is limited by computational constraints. To overcome these challenges, we propose Vecchia-inducing-points full-scale (VIF) approximations combining the strengths of global inducing points and local Vecchia approximations. Vecchia approximations excel in settings with low-dimensional inputs and moderately smooth covariance functions, while inducing point methods are better suited to high-dimensional inputs and smoother covariance […]

Ver mais