UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure in code corpora. We introduce \textbf{UniGeM}, a framework that unifies mixing and selection by treating data curation as a \textit{manifold approximation} problem without training proxy models or relying on external reference datasets. UniGeM operates hierarchically: \textbf{Macro-Exploration} learns mixing weights with stability-based clustering; \textbf{Micro-Mining} filters high-quality instances by their geometric distribution to ensure logical consistency. Validated by training 8B and 16B MoE models on 100B tokens, UniGeM achieves \textbf{2.0$\times$ data efficiency} over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.

The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understanding

Explanations are central to human cognition, yet AI systems often produce outputs that are difficult to understand. While symbolic AI offers a transparent foundation for interpretability, raw logical traces often impose a high extraneous cognitive load. We investigate how formal abstractions, specifically removal and clustering, impact human reasoning performance and cognitive effort. Utilizing Answer Set Programming (ASP) as a formal framework, we define a notion of irrelevant details to be abstracted over to obtain simplified explanations. Our cognitive experiments, in which participants classified stimuli across domains with explanations derived from an answer set program, show that clustering details significantly improve participants' understanding, while removal of details significantly reduce cognitive effort, supporting the hypothesis that abstraction enhances human-centered symbolic explanations.

NeuralFLoC: Neural Flow-Based Joint Registration and Clustering of Functional Data

Clustering functional data in the presence of phase variation is challenging, as temporal misalignment can obscure intrinsic shape differences and degrade clustering performance. Most existing approaches treat registration and clustering as separate tasks or rely on restrictive parametric assumptions. We present \textbf{NeuralFLoC}, a fully unsupervised, end-to-end deep learning framework for joint functional registration and clustering based on Neural ODE-driven diffeomorphic flows and spectral clustering. The proposed model learns smooth, invertible warping functions and cluster-specific templates simultaneously, effectively disentangling phase and amplitude variation. We establish universal approximation guarantees and asymptotic consistency for the proposed framework. Experiments on functional benchmarks show state-of-the-art performance in both registration and clustering, with robustness to missing data, irregular sampling, and noise, while maintaining scalability. Code is available at https://anonymous.4open.science/r/NeuralFLoC-FEC8.

Fedcompass: Federated Clustered and Periodic Aggregation Framework for Hybrid Classical-Quantum Models

Federated learning enables collaborative model training across decentralized clients under privacy constraints. Quantum computing offers potential for alleviating computational and communication burdens in federated learning, yet hybrid classical-quantum federated learning remains susceptible to performance degradation under non-IID data. To address this,we propose FEDCOMPASS, a layered aggregation framework for hybrid classical-quantum federated learning. FEDCOMPASS employs spectral clustering to group clients by class distribution similarity and performs cluster-wise aggregation for classical feature extractors. For quantum parameters, it uses circular mean aggregation combined with adaptive optimization to ensure stable global updates. Experiments on three benchmark datasets show that FEDCOMPASS improves test accuracy by up to 10.22% and enhances convergence stability under non-IID settings, outperforming six strong federated learning baselines.

Tri-Hybrid Holographic Beamforming for Integrated Sensing and Communication

Integrated sensing and communication (ISAC) can perform both communication and sensing tasks using the same frequency band and hardware, making it a key technology for 6G. As a low-cost implementation for large-scale antenna arrays, reconfigurable holographic surfaces (RHSs) can be integrated into ISAC systems to realize the holographic ISAC paradigm, where enlarged radiation apertures achieve significant beamforming gains. In this paper, we investigate the tri-hybrid holographic ISAC framework, where the beamformer comprises digital, analog, and RHS-based electromagnetic (EM) layers. The analog layer employs a small number of phase shifters (PSs) to provide subarray-level phase control for the amplitude-modulated RHSs. Tri-hybrid beamforming provides a pathway for low-cost large-scale holographic ISAC. However, compared to conventional ISAC systems, it is challenging to achieve joint subarray-level phase control via PSs and element-level radiation amplitude control via RHSs for holographic ISAC. To address this, we present a tri-hybrid holographic ISAC scheme that minimizes sensing waveform error while satisfying the minimum user rate requirement. A joint optimization approach for PS phases and RHS amplitude responses is designed to address inter-layer coupling and distinct feasible regions. Theoretical analyses reveal that the optimized amplitude responses cluster near boundary values, i.e., 1-bit amplitude control, to reduce hardware and algorithmic complexity. Simulation results show that the proposed scheme achieves a controllable performance trade-off between communication and sensing tasks. Measured RHS beam gain validates the enhancement of holographic beamforming through subarray-level phase shifting. Moreover, as the number of RHS elements increases, the proposed approach exceeds the performance of conventional hybrid beamforming while significantly reducing the number of PSs.

Weighted Sum-of-Trees Model for Clustered Data

Clustered data, which arise when observations are nested within groups, are incredibly common in clinical, education, and social science research. Traditionally, a linear mixed model, which includes random effects to account for within-group correlation, would be used to model the observed data and make new predictions on unseen data. Some work has been done to extend the mixed model approach beyond linear regression into more complex and non-parametric models, such as decision trees and random forests. However, existing methods are limited to using the global fixed effects for prediction on data from out-of-sample groups, effectively assuming that all clusters share a common outcome model. We propose a lightweight sum-of-trees model in which we learn a decision tree for each sample group. We combine the predictions from these trees using weights so that out-of-sample group predictions are more closely aligned with the most similar groups in the training data. This strategy also allows for inference on the similarity across groups in the outcome prediction model, as the unique tree structures and variable importances for each group can be directly compared. We show our model outperforms traditional decision trees and random forests in a variety of simulation settings. Finally, we showcase our method on real-world data from the sarcoma cohort of The Cancer Genome Atlas, where patient samples are grouped by sarcoma subtype.

OD-DEAL: Dynamic Expert-Guided Adversarial Learning with Online Decomposition for Scalable Capacitated Vehicle Routing

Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of heuristics and the limited generalization of neural solvers on massive graphs. We propose OD-DEAL, an adversarial learning framework that tightly integrates hybrid genetic search (HGS) and online barycenter clustering (BCC) decomposition, and leverages high-fidelity knowledge distillation to transfer expert heuristic behavior. OD-DEAL trains a graph attention network (GAT)-based generative policy through a minimax game, in which divide-and-conquer strategies from a hybrid expert are distilled into dense surrogate rewards. This enables high-quality, clustering-free inference on large-scale instances. Empirical results demonstrate that OD-DEAL achieves state-of-the-art (SOTA) real-time CVRP performance, solving 10000-node instances with near-constant neural scaling. This uniquely enables the sub-second, heuristic-quality inference required for dynamic large-scale deployment.

NPCNet: Navigator-Driven Pseudo Text for Deep Clustering of Early Sepsis Phenotyping

Sepsis is a heterogeneous syndrome. Identifying clinically distinct phenotypes may enable more precise treatment strategies. In recent years, many researchers have applied clustering algorithms to sepsis patients. However, the clustering process rarely incorporates clinical relevance, potentially limiting to reflect clinically distinct phenotypes. We propose NPCNet, a novel deep clustering network with a target navigator that integrates temporal Electronic Health Records (EHRs) to better align sepsis phenotypes with clinical significance. We identify four sepsis phenotypes ($α$, $β$, $γ$, and $δ$) with divergence in SOFA trajectories. Notably, while $α$ and $δ$ phenotypes both show severe conditions in the early stage, NPCNet effectively differentiates patients who are likely to improve ($α$) from those at risk of deterioration ($δ$). Furthermore, through the treatment effect analysis, we discover that $α$, $β$, and $δ$ phenotypes may benefit from early vasopressor administration. The results show that NPCNet enhances precision treatment strategies by uncovering clinically distinct phenotypes.

Quantization-Aware Regularizers for Deep Neural Networks Compression

Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained devices. As a result, model compression has become essential, and -- among compression techniques -- weight quantization is largely used and particularly effective, yet it typically introduces a non-negligible accuracy drop. However, it is usually applied to already trained models, without influencing how the parameter space is explored during the learning phase. In contrast, we introduce per-layer regularization terms that drive weights to naturally form clusters during training, integrating quantization awareness directly into the optimization process. This reduces the accuracy loss typically associated with quantization methods while preserving their compression potential. Furthermore, in our framework quantization representatives become network parameters, marking, to the best of our knowledge, the first approach to embed quantization parameters directly into the backpropagation procedure. Experiments on CIFAR-10 with AlexNet and VGG16 models confirm the effectiveness of the proposed strategy.

USS-Nav: Unified Spatio-Semantic Scene Graph for Lightweight UAV Zero-Shot Object Navigation

Zero-Shot Object Navigation in unknown environments poses significant challenges for Unmanned Aerial Vehicles (UAVs) due to the conflict between high-level semantic reasoning requirements and limited onboard computational resources. To address this, we present USS-Nav, a lightweight framework that incrementally constructs a Unified Spatio-Semantic scene graph and enables efficient Large Language Model (LLM)-augmented Zero-Shot Object Navigation in unknown environments. Specifically, we introduce an incremental Spatial Connectivity Graph generation method utilizing polyhedral expansion to capture global geometric topology, which is dynamically partitioned into semantic regions via graph clustering. Concurrently, open-vocabulary object semantics are instantiated and anchored to this topology to form a hierarchical environmental representation. Leveraging this hierarchical structure, we present a coarse-to-fine exploration strategy: LLM grounded in the scene graph's semantics to determine global target regions, while a local planner optimizes frontier coverage based on information gain. Experimental results demonstrate that our framework outperforms state-of-the-art methods in terms of computational efficiency and real-time update frequency (15 Hz) on a resource-constrained platform. Furthermore, ablation studies confirm the effectiveness of our framework, showing substantial improvements in Success weighted by Path Length (SPL). The source code will be made publicly available to foster further research.