arXiv:2603.11114v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models through conditional computation, yet the routing mechanisms responsible for expert selection remain poorly understood. In this work, we introduce routing signatures, a vector representation…
arXiv:2603.11117v1 Announce Type: new Abstract: Tree-based models are widely recognized for their interpretability and have proven effective in various application domains, particularly in high-stakes domains. However, learning decision trees (DTs) poses a significant challenge due to their combinatorial complexity and…
arXiv:2603.11099v1 Announce Type: new Abstract: The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. In this work, we introduce a graph…
arXiv:2603.11094v1 Announce Type: new Abstract: Streaming sources of data are becoming more common as the ability to collect data in real-time grows. A major concern in dealing with data streams is concept drift, a change in the distribution of data…
arXiv:2603.11090v1 Announce Type: new Abstract: Prior-data fitted networks (PFNs) have emerged as powerful foundation models for tabular causal inference, yet their extension to time series remains limited by the absence of synthetic data generators that provide interventional targets. Existing time…
arXiv:2603.10001v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit inequalities with respect to various cultural contexts. Most prominent open-weights models are trained on Global North data and show prejudicial behavior towards other cultures. Moreover, there is a notable lack…
arXiv:2603.11121v1 Announce Type: new Abstract: Building design optimization often depends on physics-based simulation tools such as EnergyPlus, which, although accurate, are computationally expensive and slow. Surrogate models provide a faster alternative, yet most are location-specific, and even weather-informed variants require…
arXiv:2603.11417v1 Announce Type: cross Abstract: End-to-end autonomous driving models are typically trained on multi-city datasets using supervised ImageNet-pretrained backbones, yet their ability to generalize to unseen cities remains largely unexamined. When training and evaluation data are geographically mixed, models may…
arXiv:2603.11131v1 Announce Type: new Abstract: While Quantum Convolutional Neural Networks (QCNNs) offer a theoretical paradigm for quantum machine learning, their practical implementation is severely bottlenecked by barren plateaus — the exponential vanishing of gradients — and poor empirical accuracy compared…
arXiv:2603.11965v1 Announce Type: cross Abstract: Standard Adjacency Spectral Embedding (ASE) relies on a global low-rank assumption often incompatible with the sparse, transitive structure of real-world networks, causing local geometric features to be ‘smeared’. To address this, we introduce Local Adjacency…
