Search

Edge detection has been one of the most difficult challenges in computer vision because of the difficulty in identifying the borders and edges from the real-world images including objects of varying kinds and sizes. Methods based on ensemble learning, which use a combination of backbones and attention modules, outperformed more conventional approaches, such as Sobel and Canny edge detection. Nevertheless, these algorithms are still challenged when faced with complicated scene photos. In addition, the identified edges utilizing the current methods are not refined and often include incorrect edges. In this work, we used a Cascaded Ensemble Canny operator to solve these problems and detect the object edges. The most difficult Fresh and Rotten and Berkeley datasets are used to test the suggested approach in Python. In terms of performance metrics and output picture quality, the acquired results outperform the specified edge detection networks, Comment: 2 Pages and 2 Figures

We explore the melting mechanisms of silver nanowires through molecular dynamics simulations and theoretical modelling, where we observe that two distinct mechanisms or pathways emerge that dictate how the solid-liquid interface melts during the phase transition. For wires longer than a critical length ($L>L_{\textrm{crit}}$), an Arrhenius-type diffusion model successfully predicts the solid-liquid interface velocity, highlighting diffusion-driven melting pathways. In contrast, wires shorter than the critical length ($L\leq L_{\textrm{crit}}$) exhibit unique behaviours driven by non-equilibrium effects, including rapid overheating of the solid core, stabilization of the solid-liquid interface, and the pronounced impact of higher energy densities. These mechanisms lead to accelerated melting and distinct phase transition dynamics. Our findings reveal how geometry and nanoscale effects critically shape melting behaviour, offering insights for the design and stability of nanostructures in advanced applications., Comment: 10 pages, 11 figures

Diabetic retinopathy is a leading cause of blindness around the world and demands precise AI-based diagnostic tools. Traditional loss functions in multi-class classification, such as Categorical Cross-Entropy (CCE), are very common but break down with class imbalance, especially in cases with inherently challenging or overlapping classes, which leads to biased and less sensitive models. Since a heavy imbalance exists in the number of examples for higher severity stage 4 diabetic retinopathy, etc., classes compared to those very early stages like class 0, achieving class balance is key. For this purpose, we propose the Adaptive Hybrid Focal-Entropy Loss which combines the ideas of focal loss and entropy loss with adaptive weighting in order to focus on minority classes and highlight the challenging samples. The state-of-the art models applied for diabetic retinopathy detection with AHFE revealed good performance improvements, indicating the top performances of ResNet50 at 99.79%, DenseNet121 at 98.86%, Xception at 98.92%, MobileNetV2 at 97.84%, and InceptionV3 at 93.62% accuracy. This sheds light into how AHFE promotes enhancement in AI-driven diagnostics for complex and imbalanced medical datasets., Comment: 9 pages,7 figures

We propose an experimental scheme for performing a Bell test using momentum-entangled pairs of atoms with different masses. This proposal uses the metastable isotopes of helium 3He* and 4He* for their single-atom detection capabilities, though the approach could be generalised to other atoms. The entangled state is generated by colliding these species and manipulated via two independent atom interferometers. This method enables precise control of the relative phases of each species, overcoming previous challenges in single-species atomic momentum Bell tests. Numerical simulations of the process show that it should be possible to achieve a significant violation of Bell's inequality under realistic experimental conditions and within a quantum mechanics framework. This type of superposition is interesting from a general relativity perspective as it introduces ambiguity in determining spacetime curvature of the quantum state. Such experiments are necessary to better understand the intersection between quantum mechanics and gravity.

Given a non-negative $n \times n$ matrix viewed as a set of distances between $n$ points, we consider the property testing problem of deciding if it is a metric. We also consider the same problem for two special classes of metrics, tree metrics and ultrametrics. For general metrics, our paper is the first to consider these questions. We prove an upper bound of $O(n^{2/3}/\epsilon^{4/3})$ on the query complexity for this problem. Our algorithm is simple, but the analysis requires great care in bounding the variance on the number of violating triangles in a sample. When $\epsilon$ is a slowly decreasing function of $n$ (rather than a constant, as is standard), we prove a lower bound of matching dependence on $n$ of $\Omega (n^{2/3})$, ruling out any property testers with $o(n^{2/3})$ query complexity unless their dependence on $1/\epsilon$ is super-polynomial. Next, we turn to tree metrics and ultrametrics. While there were known upper and lower bounds, we considerably improve these bounds showing essentially tight bounds of $\tilde{O}(1/\epsilon )$ on the sample complexity. We also show a lower bound of $\Omega ( 1/\epsilon^{4/3} )$ on the query complexity. Our upper bounds are derived by doing a more careful analysis of a natural, simple algorithm. For the lower bounds, we construct distributions on NO instances, where it is hard to find a witness showing that these are not ultrametrics.

The growth of ionized hydrogen bubbles in the intergalactic medium around early luminous objects is a fundamental process during the Epoch of Reionization (EoR). In this study, we analyze bubble sizes and their evolution using the state-of-the-art THESAN radiation-hydrodynamics simulation suite, which self-consistently models radiation transport and realistic galaxy formation throughout a large (95.5 cMpc)^3 volume of the Universe. Analogous to the accretion and merger tree histories employed in galaxy formation simulations, we characterize the growth and merger rates of ionized bubbles by focusing on the spatially-resolved redshift of reionization. By tracing the chronological expansion of bubbles, we partition the simulation volume and construct a natural ionization history. We identify three distinct stages of ionized bubble growth: (1) initial slow expansion around the earliest ionizing sources seeding formation sites, (2) accelerated growth through percolation as bubbles begin to merge, and (3) rapid expansion dominated by the largest bubble. Notably, we find that the largest bubble emerges by z=9-10, well before the midpoint of reionization. This bubble becomes dominant during the second growth stage, and defines the third stage by rapidly expanding to eventually encompass the remainder of the simulation volume and becoming one of the few bubbles actively growing. Additionally, we observe a sharp decline in the number of bubbles with radii around ~10 cMpc compared to smaller sizes, indicating a characteristic scale in the final segmented bubble size distribution. Overall, these chronologically sequenced spatial reconstructions offer crucial insights into the physical mechanisms driving ionized bubble growth during the EoR and provide a framework for interpreting the structure and evolution of reionization itself., Comment: 17 pages, 23 figures. Comments welcome. Please visit www.thesan-project.com for more details

This study explores the potential of the Ping 360 sonar device, primarily used for navigation, in detecting complex underwater obstacles. The key motivation behind this research is the device's affordability and open-source nature, offering a cost-effective alternative to more expensive imaging sonar systems. The investigation focuses on understanding the behaviour of the Ping 360 in controlled environments and assessing its suitability for object detection, particularly in scenarios where human operators are unavailable for inspecting offshore structures in shallow waters. Through a series of carefully designed experiments, we examined the effects of surface reflections and object shadows in shallow underwater environments. Additionally, we developed a manually annotated sonar image dataset to train a U-Net segmentation model. Our findings indicate that while the Ping 360 sonar demonstrates potential in simpler settings, its performance is limited in more cluttered or reflective environments unless extensive data pre-processing and annotation are applied. To our knowledge, this is the first study to evaluate the Ping 360's capabilities for complex object detection. By investigating the feasibility of low-cost sonar devices, this research provides valuable insights into their limitations and potential for future AI-based interpretation, marking a unique contribution to the field., Comment: This work is currently under review. This is a pre-print

We study normal crossings compactifications of the moduli space of maps $\mathcal{M}_{g, n}(\mathbb{P}^r, d)$, for $g = 0$ and $g = 1$. In each case we explicitly determine the dual boundary complex, and prove that it admits a natural interpretation as a moduli space of decorated metric graphs. We prove that the dual complexes are contractible when $r \geq 1$ and $d > g$. When $g = 1$, our result depends on a new understanding of the connected components of boundary strata in the Vakil--Zinger desingularization and its modular interpretation by Ranganathan--Santos-Parker--Wise.

The self-assembly of pyridyl-functionalized triazine (T4PT) was studied on Au(111) using low-temperature scanning tunneling microscopy (STM) under ultra-high vacuum conditions combined with density functional theory (DFT) calculations. In particular, we investigated the effect of temperature on the intermolecular interactions within the assemblies. STM measurements revealed that T4PT molecules form a well-ordered, close-packed structure, with the molecules adopting a planar conformation parallel to the Au surface for coverages $\leq1$ monolayer upon room temperature deposition. The intermolecular interactions stabilizing the self-assembled arrangement is based on a combination of hydrogen bonding and weak van der Waals forces. Upon post-deposition annealing, the assemblies are additionally stabilized by metal-ligand bonding between the pyridyl ligands and native Au adatoms. Further post-deposition annealing at temperatures above $200^{\circ}$C led to the breaking of the N-Au bonds with the molecular assemblies transforming into a second close-packed hydrogen bonded structure. For temperatures exceeding $230^{\circ}$C, few covalently linked dimers formed, most likely as a result of CH-bond activation. We rationalize the kinetically-driven structure formation by unveiling the interaction strengths of the bonding motifs using DFT and compare the molecular conformation to the structurally similar pyridyl-functionalized benzene (T4PB).

In many industrial applications, it is common that the graph embeddings generated from training GNNs are used in an ensemble model where the embeddings are combined with other tabular features (e.g., original node or edge features) in a downstream ML task. The tabular features may even arise naturally if, e.g., one tries to build a graph such that some of the node or edge features are stored in a tabular format. Here we address the problem of explaining the output of such ensemble models for which the input features consist of learned neural graph embeddings combined with additional tabular features. We propose MBExplainer, a model-agnostic explanation approach for downstream models with augmented graph embeddings. MBExplainer returns a human-legible triple as an explanation for an instance prediction of the whole pipeline consisting of three components: a subgraph with the highest importance, the topmost important nodal features, and the topmost important augmented downstream features. A game-theoretic formulation is used to take the contributions of each component and their interactions into account by assigning three Shapley values corresponding to their own specific games. Finding the explanation requires an efficient search through the corresponding local search spaces corresponding to each component. MBExplainer applies a novel multilevel search algorithm that enables simultaneous pruning of local search spaces in a computationally tractable way. In particular, three interweaved Monte Carlo Tree Search are utilized to iteratively prune the local search spaces. MBExplainer also includes a global search algorithm that uses contextual bandits to efficiently allocate pruning budget among the local search spaces. We show the effectiveness of MBExplainer by presenting a set of comprehensive numerical examples on multiple public graph datasets for both node and graph classification tasks.

We present a novel model of a coupled hydrogen and electricity market on the intraday time scale, where hydrogen gas is used as a storage device for the electric grid. Electricity is produced by renewable energy sources or by extracting hydrogen from a pipeline that is shared by non-cooperative agents. The resulting model is a generalized Nash equilibrium problem. Under certain mild assumptions, we prove that an equilibrium exists. Perspectives for future work are presented., Comment: 2 figures

Desert locusts are notorious agriculture pests prompting billions in losses and global food scarcity concerns. With billions of these locusts invading agrarian lands, this is no longer a thing of the past. This study taps into the existing doppler weather radar (DWR) infrastructure which was originally deployed for meteorological applications. This study demonstrates a systematic approach to distinctly identify and track concentrations of desert locust swarms in near real time using single polarization radars. Findings reveal the potential to establish early warning systems with lead times of around 7 hours and spatial coverage of approximately 100 kilometers. Embracing these technological advancements are crucial to safeguard agricultural landscapes and upload global food security., Comment: 18 pages, 5 figures

Graphs play a crucial role in data mining and machine learning, representing real-world objects and interactions. As graph datasets grow, managing large, decentralized subgraphs becomes essential, particularly within federated learning frameworks. These frameworks face significant challenges, including missing neighbor information, which can compromise model reliability in safety-critical settings. Deployment of federated learning models trained in such settings necessitates quantifying the uncertainty of the models. This study extends the applicability of Conformal Prediction (CP), a well-established method for uncertainty quantification, to federated graph learning. We specifically tackle the missing links issue in distributed subgraphs to minimize its adverse effects on CP set sizes. We discuss data dependencies across the distributed subgraphs and establish conditions for CP validity and precise test-time coverage. We introduce a Variational Autoencoder-based approach for reconstructing missing neighbors to mitigate the negative impact of missing data. Empirical evaluations on real-world datasets demonstrate the efficacy of our approach, yielding smaller prediction sets while ensuring coverage guarantees.

Integrating diverse data modalities is crucial for enhancing the performance of personalized recommendation systems. Traditional models, which often rely on singular data sources, lack the depth needed to accurately capture the multifaceted nature of item features and user behaviors. This paper introduces a novel framework for multi-behavior recommendations, leveraging the fusion of triple-modality, which is visual, textual, and graph data through alignment with large language models (LLMs). By incorporating visual information, we capture contextual and aesthetic item characteristics; textual data provides insights into user interests and item features in detail; and graph data elucidates relationships within the item-behavior heterogeneous graphs. Our proposed model called Triple Modality Fusion (TMF) utilizes the power of LLMs to align and integrate these three modalities, achieving a comprehensive representation of user behaviors. The LLM models the user's interactions including behaviors and item features in natural languages. Initially, the LLM is warmed up using only natural language-based prompts. We then devise the modality fusion module based on cross-attention and self-attention mechanisms to integrate different modalities from other models into the same embedding space and incorporate them into an LLM. Extensive experiments demonstrate the effectiveness of our approach in improving recommendation accuracy. Further ablation studies validate the effectiveness of our model design and benefits of the TMF.

We present a new formulation of the central moment lattice Boltzmann (LB) method based on a continuous Fokker-Planck (FP) kinetic model, originally proposed for stochastic diffusive-drift processes (e.g., Brownian dynamics), by adapting it as a collision model for the continuous Boltzmann equation (CBE) for fluid dynamics. The FP collision model has several desirable properties, including its ability to preserve the quadratic nonlinearity of the CBE, unlike that based on the common Bhatnagar-Gross-Krook model. Rather than using an equivalent Langevin equation as a proxy, we construct our approach by directly matching the changes in different discrete central moments independently supported by the lattice under collision to those given by the CBE under the FP-guided collision model. This can be interpreted as a new path for the collision process in terms of the relaxation of the various central moments to 'equilibria', which we term as the Markovian central moment attractors that depend on a diffusion coefficient tensor. The construction of the method using central moments rather than via distribution functions facilitates its numerical implementation and analysis. We show its consistency to the Navier-Stokes equations via a Chapman-Enskog analysis and elucidate the choice of the diffusion coefficient based on the second order moments in accurately representing flows at relatively low viscosities. We will demonstrate the accuracy and robustness of our new central moment FP-LB formulation, termed as the FPC-LBM, using the D3Q27 lattice for simulations of a variety of flows, including wall-bounded turbulent flows. We show that the FPC-LBM is more stable than other existing LB schemes based on central moments, while avoiding numerical hyperviscosity effects in flow simulations at relatively very low physical fluid viscosities through a refinement to a model founded on kinetic theory., Comment: 73 pages, 17 figures

One of the most challenging problems in the computational study of localization in quantum manybody systems is to capture the effects of rare events, which requires sampling over exponentially many disorder realizations. We implement an efficient procedure on a quantum processor, leveraging quantum parallelism, to efficiently sample over all disorder realizations. We observe localization without disorder in quantum many-body dynamics in one and two dimensions: perturbations do not diffuse even though both the generator of evolution and the initial states are fully translationally invariant. The disorder strength as well as its density can be readily tuned using the initial state. Furthermore, we demonstrate the versatility of our platform by measuring Renyi entropies. Our method could also be extended to higher moments of the physical observables and disorder learning.

The ability to steer AI behavior is crucial to preventing its long term dangerous and catastrophic potential. Representation Engineering (RepE) has emerged as a novel, powerful method to steer internal model behaviors, such as "honesty", at a top-down level. Understanding the steering of representations should thus be placed at the forefront of alignment initiatives. Unfortunately, current efforts to understand plasticity at this level are highly neglected. This paper aims to bridge the knowledge gap and understand how LLM representation stability, specifically for the concept of "honesty", and model plasticity evolve by applying steering vectors extracted at different fine-tuning stages, revealing differing magnitudes of shifts in model behavior. The findings are pivotal, showing that while early steering exhibits high plasticity, later stages have a surprisingly responsive critical window. This pattern is observed across different model architectures, signaling that there is a general pattern of model plasticity that can be used for effective intervention. These insights greatly contribute to the field of AI transparency, addressing a pressing lack of efficiency limiting our ability to effectively steer model behavior.

A central problem related to transformers can be stated as follows: given two $n \times d$ matrices $Q$ and $K$, and a non-negative function $f$, define the matrix $A$ as follows: (1) apply the function $f$ to each entry of the $n \times n$ matrix $Q K^T$, and then (2) normalize each of the row sums of $A$ to be equal to $1$. The matrix $A$ can be computed in $O(n^2 d)$ time assuming $f$ can be applied to a number in constant time, but the quadratic dependence on $n$ is prohibitive in applications where it corresponds to long context lengths. For a large class of functions $f$, we show how to find all the ``large attention scores", i.e., entries of $A$ which are at least a positive value $\varepsilon$, in time with linear dependence on $n$ (i.e., $n \cdot \textrm{poly}(d/\varepsilon)$) for a positive parameter $\varepsilon > 0$. Our class of functions include all functions $f$ of the form $f(x) = |x|^p$, as explored recently in transformer models. Using recently developed tools from randomized numerical linear algebra, we prove that for any $K$, there is a ``universal set" $U \subset [n]$ of size independent of $n$, such that for any $Q$ and any row $i$, the large attention scores $A_{i,j}$ in row $i$ of $A$ all have $j \in U$. We also find $U$ in $n \cdot \textrm{poly}(d/\varepsilon)$ time. Notably, we (1) make no assumptions on the data, (2) our workspace does not grow with $n$, and (3) our algorithms can be computed in streaming and parallel settings. We call the attention mechanism that uses only the subset of keys in the universal set as LevAttention since our algorithm to identify the universal set $U$ is based on leverage scores. We empirically show the benefits of our scheme for vision transformers, showing how to train new models that use our universal set while training as well, showing that our model is able to consistently select ``important keys'' during training.

Reach-Avoid-Stay (RAS) optimal control enables systems such as robots and air taxis to reach their targets, avoid obstacles, and stay near the target. However, current methods for RAS often struggle with handling complex, dynamic environments and scaling to high-dimensional systems. While reinforcement learning (RL)-based reachability analysis addresses these challenges, it has yet to tackle the RAS problem. In this paper, we propose a two-step deep deterministic policy gradient (DDPG) method to extend RL-based reachability method to solve RAS problems. First, we train a function that characterizes the maximal robust control invariant set within the target set, where the system can safely stay, along with its corresponding policy. Second, we train a function that defines the set of states capable of safely reaching the robust control invariant set, along with its corresponding policy. We prove that this method results in the maximal robust RAS set in the absence of training errors and demonstrate that it enables RAS in complex environments, scales to high-dimensional systems, and achieves higher success rates for the RAS task compared to previous methods, validated through one simulation and two high-dimensional experiments.

With hundreds of thousands of language models available on Huggingface today, efficiently evaluating and utilizing these models across various downstream, tasks has become increasingly critical. Many existing methods repeatedly learn task-specific representations of Large Language Models (LLMs), which leads to inefficiencies in both time and computational resources. To address this, we propose EmbedLLM, a framework designed to learn compact vector representations, of LLMs that facilitate downstream applications involving many models, such as model routing. We introduce an encoder-decoder approach for learning such embeddings, along with a systematic framework to evaluate their effectiveness. Empirical results show that EmbedLLM outperforms prior methods in model routing both in accuracy and latency. Additionally, we demonstrate that our method can forecast a model's performance on multiple benchmarks, without incurring additional inference cost. Extensive probing experiments validate that the learned embeddings capture key model characteristics, e.g. whether the model is specialized for coding tasks, even without being explicitly trained on them. We open source our dataset, code and embedder to facilitate further research and application.

We consider ideals in a polynomial ring generated by collections of power sum polynomials, and obtain conditions under which these define complete intersection rings, normal domains, and unique factorization domains. We also settle a key case of a conjecture of Conca, Krattenthaler, and Watanabe, and prove other results in that direction.

Lattice gauge theories (LGTs) can be employed to understand a wide range of phenomena, from elementary particle scattering in high-energy physics to effective descriptions of many-body interactions in materials. Studying dynamical properties of emergent phases can be challenging as it requires solving many-body problems that are generally beyond perturbative limits. We investigate the dynamics of local excitations in a $\mathbb{Z}_2$ LGT using a two-dimensional lattice of superconducting qubits. We first construct a simple variational circuit which prepares low-energy states that have a large overlap with the ground state; then we create particles with local gates and simulate their quantum dynamics via a discretized time evolution. As the effective magnetic field is increased, our measurements show signatures of transitioning from deconfined to confined dynamics. For confined excitations, the magnetic field induces a tension in the string connecting them. Our method allows us to experimentally image string dynamics in a (2+1)D LGT from which we uncover two distinct regimes inside the confining phase: for weak confinement the string fluctuates strongly in the transverse direction, while for strong confinement transverse fluctuations are effectively frozen. In addition, we demonstrate a resonance condition at which dynamical string breaking is facilitated. Our LGT implementation on a quantum processor presents a novel set of techniques for investigating emergent particle and string dynamics.

We study ergotropy, the maximum unitarily extractable work from a system, in two quantum chaotic models: the quantum kicked top and the kicked Ising spin chain. In an ancilla-assisted scenario, chaos enhances ergotropy when the state is known, a consequence of large entanglement production in the chaotic regime. In contrast, we establish a negative correlation between chaos and work when the state is unknown. The downside arises from chaos impeding information gain of the system from coarse-grained measurements. When both entanglement and coarse-grained measurements are present, there is competition between the two, and the ergotropy initially increases, followed by a decrease at larger kick-strengths., Comment: 10 pages, 10 figures

Scene Change Detection is a challenging task in computer vision and robotics that aims to identify differences between two images of the same scene captured at different times. Traditional change detection methods rely on training models that take these image pairs as input and estimate the changes, which requires large amounts of annotated data, a costly and time-consuming process. To overcome this, we propose ZeroSCD, a zero-shot scene change detection framework that eliminates the need for training. ZeroSCD leverages pre-existing models for place recognition and semantic segmentation, utilizing their features and outputs to perform change detection. In this framework, features extracted from the place recognition model are used to estimate correspondences and detect changes between the two images. These are then combined with segmentation results from the semantic segmentation model to precisely delineate the boundaries of the detected changes. Extensive experiments on benchmark datasets demonstrate that ZeroSCD outperforms several state-of-the-art methods in change detection accuracy, despite not being trained on any of the benchmark datasets, proving its effectiveness and adaptability across different scenarios.

Recent work has shown that Transformers trained from scratch can successfully solve various arithmetic and algorithmic tasks, such as adding numbers and computing parity. While these Transformers generalize well on unseen inputs of the same length, they struggle with length generalization, i.e., handling inputs of unseen lengths. In this work, we demonstrate that looped Transformers with an adaptive number of steps significantly improve length generalization. We focus on tasks with a known iterative solution, involving multiple iterations of a RASP-L operation - a length-generalizable operation that can be expressed by a finite-sized Transformer. We train looped Transformers using our proposed learning algorithm and observe that they learn highly length-generalizable solutions for various tasks.

Personalized outfit recommendation remains a complex challenge, demanding both fashion compatibility understanding and trend awareness. This paper presents a novel framework that harnesses the expressive power of large language models (LLMs) for this task, mitigating their "black box" and static nature through fine-tuning and direct feedback integration. We bridge the item visual-textual gap in items descriptions by employing image captioning with a Multimodal Large Language Model (MLLM). This enables the LLM to extract style and color characteristics from human-curated fashion images, forming the basis for personalized recommendations. The LLM is efficiently fine-tuned on the open-source Polyvore dataset of curated fashion images, optimizing its ability to recommend stylish outfits. A direct preference mechanism using negative examples is employed to enhance the LLM's decision-making process. This creates a self-enhancing AI feedback loop that continuously refines recommendations in line with seasonal fashion trends. Our framework is evaluated on the Polyvore dataset, demonstrating its effectiveness in two key tasks: fill-in-the-blank, and complementary item retrieval. These evaluations underline the framework's ability to generate stylish, trend-aligned outfit suggestions, continuously improving through direct feedback. The evaluation results demonstrated that our proposed framework significantly outperforms the base LLM, creating more cohesive outfits. The improved performance in these tasks underscores the proposed framework's potential to enhance the shopping experience with accurate suggestions, proving its effectiveness over the vanilla LLM based outfit generation., Comment: CIKM 2024

Foundation models pre-trained using self-supervised and weakly-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text generation, and image recognition. Recently, the Earth observation (EO) field has produced several foundation models pre-trained directly on multispectral satellite imagery (e.g., Sentinel-2) for applications like precision agriculture, wildfire and drought monitoring, and natural disaster response. However, few studies have investigated the ability of these models to generalize to new geographic locations, and potential concerns of geospatial bias -- models trained on data-rich developed countries not transferring well to data-scarce developing countries -- remain. We investigate the ability of popular EO foundation models to transfer to new geographic regions in the agricultural domain, where differences in farming practices and class imbalance make transfer learning particularly challenging. We first select six crop classification datasets across five continents, normalizing for dataset size and harmonizing classes to focus on four major cereal grains: maize, soybean, rice, and wheat. We then compare three popular foundation models, pre-trained on SSL4EO-S12, SatlasPretrain, and ImageNet, using in-distribution (ID) and out-of-distribution (OOD) evaluation. Experiments show that pre-trained weights designed explicitly for Sentinel-2, such as SSL4EO-S12, outperform general pre-trained weights like ImageNet. Furthermore, the benefits of pre-training on OOD data are the most significant when only 10--100 ID training samples are used. Transfer learning and pre-training with OOD and limited ID data show promising applications, as many developing regions have scarce crop type labels. All harmonized datasets and experimental code are open-source and available for download.

E-commerce platforms have a vast catalog of items to cater to their customers' shopping interests. Most of these platforms assist their customers in the shopping process by offering optimized recommendation carousels, designed to help customers quickly locate their desired items. Many models have been proposed in academic literature to generate and enhance the ranking and recall set of items in these carousels. Conventionally, the accompanying carousel title text (header) of these carousels remains static. In most instances, a generic text such as "Items similar to your current viewing" is utilized. Fixed variations such as the inclusion of specific attributes "Other items from a similar seller" or "Items from a similar brand" in addition to "frequently bought together" or "considered together" are observed as well. This work proposes a novel approach to customize the header generation process of these carousels. Our work leverages user-generated reviews that lay focus on specific attributes (aspects) of an item that were favorably perceived by users during their interaction with the given item. We extract these aspects from reviews and train a graph neural network-based model under the framework of a conditional ranking task. We refer to our innovative methodology as Dynamic Text Snippets (DTS) which generates multiple header texts for an anchor item and its recall set. Our approach demonstrates the potential of utilizing user-generated reviews and presents a unique paradigm for exploring increasingly context-aware recommendation systems., Comment: 7 pages, 3 figures, PAIS 2024 (ECAI)

Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs) as their superior performance typically comes from aggregating homophilous information. Increasing the GNN depth can expand the scope (i.e., receptive field), potentially finding homophily from the higher-order neighborhoods. However, uniformly expanding the scope results in subpar performance since real-world web graphs often exhibit homophily disparity between nodes. An ideal way is personalized scopes, allowing nodes to have varying scope sizes. Existing methods typically add node-adaptive weights for each hop. Although expressive, they inevitably suffer from severe overfitting. To address this issue, we formalize personalized scoping as a separate scope classification problem that overcomes GNN overfitting in node classification. Specifically, we predict the optimal GNN depth for each node. Our theoretical and empirical analysis suggests that accurately predicting the depth can significantly enhance generalization. We further propose Adaptive Scope (AS), a lightweight approach that only participates in GNN inference. AS encodes structural patterns and predicts the depth to select the best model for each node's prediction. Experimental results show that AS is highly flexible with various GNN architectures across a wide range of datasets while significantly improving accuracy.

Horospherical Schubert varieties are determined. It is shown that the stabilizer of an arbitrary point in a Schubert variety is a strongly solvable algebraic group. The connectedness of this stabilizer subgroup is discussed. Moreover, a new family of spherical varieties, called doubly spherical varieties, is introduced. It is shown that every nearly toric Schubert variety is doubly spherical., Comment: 22 pages

There has been substantial recent concern that pricing algorithms might learn to ``collude.'' Supra-competitive prices can emerge as a Nash equilibrium of repeated pricing games, in which sellers play strategies which threaten to punish their competitors who refuse to support high prices, and these strategies can be automatically learned. In fact, a standard economic intuition is that supra-competitive prices emerge from either the use of threats, or a failure of one party to optimize their payoff. Is this intuition correct? Would preventing threats in algorithmic decision-making prevent supra-competitive prices when sellers are optimizing for their own revenue? No. We show that supra-competitive prices can emerge even when both players are using algorithms which do not encode threats, and which optimize for their own revenue. We study sequential pricing games in which a first mover deploys an algorithm and then a second mover optimizes within the resulting environment. We show that if the first mover deploys any algorithm with a no-regret guarantee, and then the second mover even approximately optimizes within this now static environment, monopoly-like prices arise. The result holds for any no-regret learning algorithm deployed by the first mover and for any pricing policy of the second mover that obtains them profit at least as high as a random pricing would -- and hence the result applies even when the second mover is optimizing only within a space of non-responsive pricing distributions which are incapable of encoding threats. In fact, there exists a set of strategies, neither of which explicitly encode threats that form a Nash equilibrium of the simultaneous pricing game in algorithm space, and lead to near monopoly prices. This suggests that the definition of ``algorithmic collusion'' may need to be expanded, to include strategies without explicitly encoded threats.

In this paper, we extend the results of Grantcharov and Robitaille in 2021 on mixed tensor products and Capelli determinants to the superalgebra setting. Specifically, we construct a family of superalgebra homomorphisms $\varphi_R : U(\mathfrak{gl}(m+1|n)) \rightarrow \mathcal{D}'(m|n) \otimes U(\mathfrak{gl}(m|n))$ for a certain space of differential operators $\mathcal{D}'(m|n)$ indexed by a central element $R$ of $\mathcal{D}'(m|n) \otimes U(\mathfrak{gl}(m|n))$. We then use this homomorphism to determine the image of Gelfand generators of the center of $U(\mathfrak{gl}(m+1|n))$. We achieve this by first relating $\varphi_R$ to the corresponding Harish-Chandra homomorphisms and then proving a super-analog of Newton's formula for $\mathfrak{gl}(m)$ relating Capelli generators and Gelfand generators. We also use the homomorphism $\varphi_R$ to obtain representations of $U(\mathfrak{gl}(m+1|n))$ from those of $U(\mathfrak{gl}(m|n))$, and find conditions under which these inflations are simple. Finally, we show that for a distinguished central element $R_1$ in $\mathcal{D}'(m|n)\otimes U(\mathfrak{gl}(m|n))$, the kernel of $\varphi_{R_1}$ is the ideal of $U(\mathfrak{gl}(m+1|n))$ generated by the first Gelfand invariant $G_1$.

We investigate the redshift evolution of the concentration-mass relationship of dark matter haloes in state-of-the-art cosmological hydrodynamic simulations and their dark-matter-only counterparts. By combining the IllustrisTNG suite and the novel MillenniumTNG simulation, our analysis encompasses a wide range of box size ($50 - 740 \: \rm cMpc$) and mass resolution ($8.5 \times 10^4 - 3.1 \times 10^7 \: \rm M_{\odot}$ per baryonic mass element). This enables us to study the impact of baryons on the concentration-mass relationship in the redshift interval $0