Entropic causal inference is a recent framework for learning the causal graph between two variables from observational data by finding the information-theoretically simplest structural explanation of the data, i.e., the model with smallest entropy. In our work, we first extend the causal graph identifiability result in the two-variable setting under relaxed assumptions. We then show the first identifiability result using the entropic approach for learning causal graphs with more than two nodes. Our approach utilizes the property that ancestrality between a source node and its descendants can be determined using the bivariate entropic tests. We provide a sound sequential peeling algorithm for general graphs that relies on this property. We also propose a heuristic algorithm for small graphs that shows strong empirical performance. We rigorously evaluate the performance of our algorithms on synthetic data generated from a variety of models, observing improvement over prior work. Finally we test our algorithms on real-world datasets.

Large language models improve with scale, yet feedback-based alignment still exhibits systematic deviations from intended behavior. Motivated by bounded rationality in economics and cognitive science, we view judgment as resource-limited and feedback as a constrained channel. On this basis, we model the loop as a two-stage cascade $U \to H \to Y$ given $S$, with cognitive capacity $C_{\text{cog}|S}$ and average total capacity $\bar{C}_{\text{tot}|S}$. Our main result is a capacity-coupled Alignment Performance Interval. It pairs a data size-independent Fano lower bound proved on a separable codebook mixture with a PAC-Bayes upper bound whose KL term is controlled by the same channel via $m \, \bar{C}_{\text{tot}|S}$. The PAC-Bayes bound becomes an upper bound on the same true risk when the canonical observable loss is used and the dataset is drawn from the same mixture. Under these matched conditions, both limits are governed by a single capacity. Consequences include that, with value complexity and capacity fixed, adding labels alone cannot cross the bound; attaining lower risk on more complex targets requires capacity that grows with $\log M$; and once useful signal saturates capacity, further optimization tends to fit channel regularities, consistent with reports of sycophancy and reward hacking. The analysis views alignment as interface engineering: measure and allocate limited capacity, manage task complexity, and decide where information is spent.

We highlight a fundamental connection between information geometry and variational Bayes (VB) and discuss its consequences for machine learning. Under certain conditions, a VB solution always requires estimation or computation of natural gradients. We show several consequences of this fact by using the natural-gradient descent algorithm of Khan and Rue (2023) called the Bayesian Learning Rule (BLR). These include (i) a simplification of Bayes' rule as addition of natural gradients, (ii) a generalization of quadratic surrogates used in gradient-based methods, and (iii) a large-scale implementation of VB algorithms for large language models. Neither the connection nor its consequences are new but we further emphasize the common origins of the two fields of information geometry and Bayes with a hope to facilitate more work at the intersection of the two fields.

We consider the problem of estimating the directions of arrival (DOAs) of multiple sources from a single snapshot of an antenna array, a task with many practical applications. In such settings, the classical Bartlett beamformer is commonly used, as maximum likelihood estimation becomes impractical when the number of sources is unknown or large, and spectral methods based on the sample covariance are not applicable due to the lack of multiple snapshots. However, the accuracy and resolution of the Bartlett beamformer are fundamentally limited by the array aperture. In this paper, we propose a deep learning technique, comprising a novel architecture and training strategy, for generating a high-resolution spatial spectrum from a single snapshot. Specifically, we train a deep neural network that takes the measurements and a hypothesis angle as input and learns to output a score consistent with the capabilities of a much wider array. At inference time, a heatmap can be produced by scanning an arbitrary set of angles. We demonstrate the advantages of our trained model, named (SP)$^2$-Net, over the Bartlett beamformer and sparsity-based DOA estimation methods.

Atomic data determined by analysis of observed atomic spectra are essential for plasma diagnostics. For each low-ionisation open d- and f-subshell atomic species, around $10^3$ fine structure level energies can be determined through years of analysis of $10^4$ observable spectral lines. We propose the automation of this task by casting the analysis procedure as a Markov decision process and solving it by graph reinforcement learning using reward functions learned on historical human decisions. In our evaluations on existing spectral line lists and theoretical calculations for Co II and Nd II-III, hundreds of level energies were computed within hours, agreeing with published values in 95% of cases for Co II and 54-87% for Nd II-III. As the current efficiency in atomic fine structure determination struggles to meet growing atomic data demands from astronomy and fusion science, our new artificial intelligence approach sets the stage for closing this gap.

Deep reinforcement learning (RL) is emerging as a viable strategy for automated cyber defense (ACD). The traditional RL approach represents networks as a list of computers in various states of safety or threat. Unfortunately, these models are forced to overfit to specific network topologies, rendering them ineffective when faced with even small environmental perturbations. In this work, we frame ACD as a two-player context-based partially observable Markov decision problem with observations represented as attributed graphs. This approach allows our agents to reason through the lens of relational inductive bias. Agents learn how to reason about hosts interacting with other system entities in a more general manner, and their actions are understood as edits to the graph representing the environment. By introducing this bias, we will show that our agents can better reason about the states of networks and zero-shot adapt to new ones. We show that this approach outperforms the state-of-the-art by a wide margin, and makes our agents capable of defending never-before-seen networks against a wide range of adversaries in a variety of complex, and multi-agent environments.

A fully quantum reinforcement learning framework is developed that integrates a quantum Markov decision process, dynamic circuit-based qubit reuse, and Grover's algorithm for trajectory optimization. The framework encodes states, actions, rewards, and transitions entirely within the quantum domain, enabling parallel exploration of state-action sequences through superposition and eliminating classical subroutines. Dynamic circuit operations, including mid-circuit measurement and reset, allow reuse of the same physical qubits across multiple agent-environment interactions, reducing qubit requirements from 7*T to 7 for T time steps while preserving logical continuity. Quantum arithmetic computes trajectory returns, and Grover's search is applied to the superposition of these evaluated trajectories to amplify the probability of measuring those with the highest return, thereby accelerating the identification of the optimal policy. Simulations demonstrate that the dynamic-circuit-based implementation preserves trajectory fidelity while reducing qubit usage by 66 percent relative to the static design. Experimental deployment on IBM Heron-class quantum hardware confirms that the framework operates within the constraints of current quantum processors and validates the feasibility of fully quantum multi-step reinforcement learning under noisy intermediate-scale quantum conditions. This framework advances the scalability and practical application of quantum reinforcement learning for large-scale sequential decision-making tasks.

Abstract--Reconstructing building floor plans from point cloud data is a critical technology for indoor navigation, building information modeling (BIM), and highly accurate precise indoor measurement applications. Traditional methods, such as geometric algorithms and Mask R-CNN-based deep learning for mask segmentation, often suffer from sensitivity to noise, limited generalization, and loss of geometric details, severely impacting measurement accuracy. This study proposes an innovative framework, FloorSAM, that integrates room-height point cloud density maps with the guided segmentation capabilities of the Segment Anything Model (SAM) to enhance the precision of floor plan reconstruction from LiDAR point cloud data. By applying grid-based filtering to retain elevation point clouds near the ceiling of each region, combined with adaptive resolution projection and image enhancement techniques, a top-down density map is generated, improving the robustness and accuracy of spatial feature measurement. This framework leverages SAM's zero-shot learning to achieve high-fidelity room segmentation, remarkably enhancing reconstruction and measurement accuracy across diverse building layouts. Subsequently, leveraging SAM's zero-shot guided segmentation capabilities, high-quality room masks are generated based on adaptive prompt points, followed by a multistage filtering process to extract precise semantic masks for individual rooms. Through joint analysis of mask and point cloud modalities, contour extraction and regularization are performed, integrating semantic segmentation with geometric information to produce accurate room floor plans and recover topological relationships between rooms.

The primary objective of RL is for an agent to learn an optimal policy to control a system by minimizing a long-term loss, represented by the Q-function. This learning occurs through interactions with the environment, which is typically modeled as a Markov decision process (MDP). In most high-dimensional, real-world problems, explicitly representing the Q-function for all possible states and actions is impractical due to the "curse of dimensionality." A common solution is to approximate the Q-function using a parametric (functional) representation. This, however, introduces a fundamental trade-off between approximation accuracy and computational complexity: reducing the approximation error generally requires a large number of features in the parametric model, which in turn increases computational demands. Feature selection, achieved via a sparse representation over a large basis of functions, is an effective way to alleviate this tradeoff, mitigate overfitting, and improve sample efficiency.

Abstract-- Global data association is an essential prerequisite for robot operation in environments seen at different times or by different robots. Repetitive or symmetric data creates significant challenges for existing methods, which typically rely on maximum likelihood estimation or maximum consensus to produce a single set of associations. However, in ambiguous scenarios, the distribution of solutions to global data association problems is often highly multimodal, and such single-solution approaches frequently fail. In this work, we introduce a data association framework that leverages approximate Bayesian inference to capture multiple solution modes to the data association problem, thereby avoiding premature commitment to a single solution under ambiguity. Our approach represents hypothetical solutions as particles that evolve according to a deterministic or randomized update rule to cover the modes of the underlying solution distribution. Furthermore, we show that our method can incorporate optimization constraints imposed by the data association formulation and directly benefit from GPU-parallelized optimization. Extensive simulated and real-world experiments with highly ambiguous data show that our method correctly estimates the distribution over transformations when registering point clouds or object maps. I. INTRODUCTION Data association is essential in many robotic applications, enabling key perception technologies such as dynamic object tracking [1]-[3] and simultaneous localization and mapping (SLAM) [4]-[6]. In these scenarios, robots must recognize when an object or feature they are currently observing is the same as something they (or another robot) may have seen from a different perspective. Without correct data association, the environment representation may be inconsistent, leading to undesirable behaviors in downstream tasks (e.g., incorrect associations in loop closure detection can lead to dramatically distorted maps [6]).