I spent years calling models via API : Bedrock, Sagemaker, Anthropic. This week was about understanding what’s actually happening inside the box, and why that matters for building systems around it. Coming into this project, I had built production AI systems on AWS Bedrock using flows, agents. I knew how to wire models into applications. What I didn’t know was what the models were actually doing with the text I gave them, why RAG works at all, or […]

Ver mais

Your warehouse already contains an implicit “analytics brain” in the form of years of SQL; SQL embeddings make that brain searchable and reusable. Embedding SQL + query metadata enables natural-language questions to map onto previously validated query patterns instead of generating SQL from scratch. The most effective setups separate retrieval (find similar queries) from generation (adapt/combine them) and always pass domain + metric hints. This shifts analytics from dashboard-hunting to decision flows backed by a shared SQL memory, […]

Ver mais

There’s a very specific kind of productivity that only engineers know. It looks like progress. It feels like progress. It even *logs* like progress. But nothing ships. I know this because I’ve lived there. For weeks. Sometimes months. Writing code. Rewriting code. Refactoring code that hasn’t offended anyone yet. Stashing changes like they’re radioactive. Telling myself, *“I’m being careful.”* No. I was being scared. Let’s call it what it is. This isn’t engineering. This is avoidance in a […]

Ver mais

arXiv:2602.20231v1 Announce Type: new Abstract: Latent action representations learned from unlabeled videos have recently emerged as a promising paradigm for pretraining vision-language-action (VLA) models without explicit robot action supervision. However, latent actions derived solely from RGB observations primarily encode appearance-driven dynamics and lack explicit 3D geometric structure, which is essential for precise and contact-rich manipulation. To address this limitation, we introduce UniLACT, a transformer-based VLA model that incorporates geometric structure through depth-aware latent pretraining, enabling downstream policies to […]

Ver mais

Deep learning models are being used for the analysis of parametric statistical models based on simulation-only frameworks. Bayesian models using normalizing flows simulate data from a prior distribution and are composed of two deep neural networks: a summary network that learns a sufficient statistic for the parameter and a normalizing flow that conditional on the summary network can approximate the posterior distribution. Here, we explore frequentist models that are based on a single summary network. During training, input […]

Ver mais

arXiv:2506.04166v2 Announce Type: replace-cross Abstract: Nearest neighbor (NN) methods have re-emerged as competitive tools for matrix completion, offering strong empirical performance and recent theoretical guarantees, including entry-wise error bounds, confidence intervals, and minimax optimality. Despite their simplicity, recent work has shown that NN approaches are robust to a range of missingness patterns and effective across diverse applications. This paper introduces N$^2$, a unified Python package and testbed that consolidates a broad class of NN-based methods through a modular, […]

Ver mais

arXiv:2601.06262v1 Announce Type: cross Abstract: Community detection is a fundamental task in data analysis. Block models form a standard approach to partition nodes according to a graph model, facilitating the analysis and interpretation of the network structure. By grouping nodes with similar connection patterns, they enable the identification of a wide variety of underlying structures. The degree-corrected block model (DCBM) is an established model that accounts for the heterogeneity of node degrees. However, existing inference methods for the […]

Ver mais

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility by design. Our method, LSFlow, learns a emph{stochastic} policy […]

Ver mais

arXiv:2601.18987v1 Announce Type: new Abstract: Determining whether a program terminates is a central problem in computer science. Turing’s foundational result established the Halting Problem as undecidable, showing that no algorithm can universally determine termination for all programs and inputs. Consequently, automatic verification tools approximate termination, sometimes failing to prove or disprove; these tools rely on problem-specific architectures and abstractions, and are usually tied to particular programming languages. Recent success and progress in large language models (LLMs) raises the […]

Ver mais