Hey We speak of the “Data Wall,” but for Indian languages, it’s a data abyss. Hinglish corpora are small, toxic-scraped, or lose the Indian flavor after translation. I’m working on a pipeline for the generation of privacy-preserving synthetic Hinglish conversational data. Pipeline: -Seed: 35k real Hinglish conversations (quality: 98.67) -Architecture: GaussianCopula + custom speaker oversampling Goal: scale minority dialects while maintaining code-mix patterns Reality check (10k rows): Privacy: AUC 0.95 (membership inference) Quality: 0.6897 (target ≥ 0.75) Word […]

Ver mais

arXiv:2602.15926v1 Announce Type: new Abstract: Object detection has compelling applications over a range of domains, including human-computer interfaces, security and video surveillance, navigation and road traffic monitoring, transportation systems, industrial automation healthcare, the world of Augmented Reality (AR) and Virtual Reality (VR), environment monitoring and activity identification. Applications of real time object detection in all these areas provide dynamic analysis of the visual information that helps in immediate decision making. Furthermore, advanced deep learning algorithms leverage the progress […]

Ver mais

arXiv:2602.15901v1 Announce Type: new Abstract: Autonomous sailboats are well suited for long-duration ocean observation due to their wind-driven endurance. However, their performance is highly anisotropic and strongly influenced by inhomogeneous and time-varying wind and current fields, limiting the effectiveness of existing coverage methods such as boustrophedon sweeping. Planning under these environmental and maneuvering constraints remains underexplored. This paper presents a spatiotemporal coverage path planning framework tailored to autonomous sailboats, combining (1) topology-based morphological constraints in the spatial domain […]

Ver mais

After 8 years building production ML systems (in data quality, entity resolution, diagnostics), I keep running into the same problem: Models with great offline metrics fail in production because they learn correlations, not causal mechanisms. I just started a 5-part series on building causal ML systems on the NeoForge Labs research blog. Part 1 covers: Why correlation fails – The ice cream/drowning example, but with real production failures Pearl’s Ladder of Causation – Association, Intervention, Counterfactuals Practical implications […]

Ver mais

arXiv:2404.09113v4 Announce Type: replace Abstract: Variational inference (VI) has emerged as a popular method for approximate inference for high-dimensional Bayesian models. In this paper, we propose a novel VI method that extends the naive mean field via entropic regularization, referred to as $Xi$-variational inference ($Xi$-VI). $Xi$-VI has a close connection to the entropic optimal transport problem and benefits from the computationally efficient Sinkhorn algorithm. We show that $Xi$-variational posteriors effectively recover the true posterior dependency, where the dependence […]

Ver mais

New international student enrollment at U.S. colleges and universities plunged 17% in fall 2025, the steepest non-pandemic decline in over a decade, according to data released today by the Institute of International Education. More than half of the 825 institutions surveyed reported decreases, with a majority citing visa application concerns. lead , Neal McCluskey, Director of Cato’s Center for Educational Freedom, warns: “Dropping international student enrollment is troubling for American higher education and the country. The United States […]

Ver mais

Floating-point neural networks dominate modern machine learning but incur substantial inference cost, motivating interest in Boolean networks for resource-constrained settings. However, learning compact and accurate Boolean networks is challenging due to their combinatorial nature. In this work, we address this challenge from three different angles: learned connections, compact convolutions and adaptive discretization. First, we propose a novel strategy to learn efficient connections with no additional parameters and negligible computational overhead. Second, we introduce a novel convolutional Boolean architecture […]

Ver mais