Networks of interdependent industrial assets (clients) are tightly coupled through physical processes and control inputs, raising a key question: how would the output of one client change if another client were operated differently? This is difficult to answer because client-specific data are high-dimensional and private, making centralization of raw data infeasible. Each client also maintains proprietary local models that cannot be modified. We propose a federated framework for causal representation learning in state-space systems that captures interdependencies among […]

Ver mais

arXiv:2603.27320v1 Announce Type: cross Abstract: Retrospective causal questions ask what would have happened to an observed individual had they received a different treatment. We study the problem of estimating $mu(x,y)=mathbb{E}[Y(1)mid X=x,Y(0)=y]$, the expected counterfactual outcome for an individual with covariates $x$ and observed outcome $y$, and constructing valid prediction intervals under the Neyman-Rubin superpopulation model. This quantity is generally not identified without additional assumptions. To link the observed and unobserved potential outcomes, we work with a cross-world correlation […]

Ver mais

Release: llm-echo 0.4 Prompts now have the input_tokens and output_tokens fields populated on the response. Tags: llm

Ver mais

State-of-the-art deep reinforcement learning (RL) methods have achieved remarkable performance in continuous control tasks, yet their computational complexity is often incompatible with the constraints of resource-limited hardware, due to their reliance on replay buffers, batch updates, and target networks. The emerging paradigm of streaming deep RL addresses this limitation through purely online updates, achieving strong empirical performance on standard benchmarks. In this work, we propose two novel streaming deep RL algorithms, Streaming Soft Actor-Critic (S2AC) and Streaming Deterministic […]

Ver mais

We present a new self-supervised machine learning approach for symbolic simplification of complex mathematical expressions. Training data is generated by scrambling simple expressions and recording the inverse operations, creating oracle trajectories that provide both goal states and explicit paths to reach them. A permutation-equivariant, transformer-based policy network is then trained on this data step-wise to predict the oracle action given the input expression. We demonstrate this approach on two problems in high-energy physics: dilogarithm reduction and spinor-helicity scattering […]

Ver mais

Machine Learning (ML) is fundamentally reshaping education, offering tools to personalize instruction, automate assessment, and predict student outcomes. This paper provides a comprehensive overview of ML’s role in education, tracing its evolution from early computer-assisted instruction to today’s generative artificial intelligence (AI). We explore key applications, including intelligent tutoring systems, early warning systems for at-risk students, and automated essay scoring, highlighting their potential to address the long-standing challenge of individualized learning at scale. However, this technological integration is […]

Ver mais

In medical diagnostics, integrating quantum computing with deep learning offers potential improvements in sensitivity and computational efficiency. This study introduces two models: LiteSpineNet, a streamlined CNN, and HQ-LiteSpineNet, its hybrid quantum counterpart that incorporates a novel seven-qubit variational feature extraction block for multiclass spine lesion classification. Using the VinDr-SpineXR dataset of 12,000 X-ray images across eight classes, we show that both models achieve strong performance while requiring substantially fewer parameters than state-of-the-art methods. LiteSpineNet attains 76.81% test accuracy, […]

Ver mais

arXiv:2601.14283v1 Announce Type: new Abstract: Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a single algorithmic category, cross-algorithm comparisons remain scarce. In this paper, to fill the gap, we establish a benchmark to evaluate the performance of fifteen models across these different algorithmic foundations by assessing the pharmaceutical properties of the generated molecules […]

Ver mais

arXiv:2601.10901v1 Announce Type: new Abstract: We explore a novel problem in streaming submodular maximization, inspired by the dynamics of news-recommendation platforms. We consider a setting where users can visit a news website at any time, and upon each visit, the website must display up to $k$ news items. User interactions are inherently stochastic: each news item presented to the user is consumed with a certain acceptance probability by the user, and each news item covers certain topics. Our […]

Ver mais