arXiv:2607.09211v1 Announce Type: new Abstract: While traditional evolutionary algorithms hard-code reproduction, self-replication can emerge spontaneously within digital ``primordial soups''. This paper investigates the co-evolution of this…
arXiv:2607.09202v1 Announce Type: cross Abstract: Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation. This work argues that forgetting should instead…
arXiv:2607.09480v1 Announce Type: cross Abstract: The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational…
arXiv:2606.20858v2 Announce Type: replace-cross Abstract: The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the progression…
arXiv:2510.21742v3 Announce Type: replace-cross Abstract: The statistics of correlations are central quantities characterizing the collective dynamics of recurrent neural networks. We derive exact expressions for the…
arXiv:2607.08883v1 Announce Type: new Abstract: Behavioral alignment in large language models often masks fragile internal safety representations. Recent work suggests that refusal behavior is mediated by…
arXiv:2607.08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space. In deep learning, this…
arXiv:2606.18853v3 Announce Type: replace-cross Abstract: A recent line of work has reframed individual decision trees as linear models on engineered features associated with their splits, opening…
arXiv:2607.08837v1 Announce Type: new Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject…
arXiv:2511.15615v2 Announce Type: replace-cross Abstract: This paper presents a tractable algorithm for estimating an unknown Lipschitz function from noisy observations and establishes an upper bound on…
arXiv:2607.08789v1 Announce Type: new Abstract: Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback. We show that the regret of any such update…
arXiv:2004.05813v3 Announce Type: replace-cross Abstract: Suppose that we are given independent, identically distributed random samples $x_1,cdots,x_n$ from a mixture at most $k$ many $d$-dimensional spherical Gaussian…
arXiv:2607.08786v1 Announce Type: new Abstract: With the growing deployment of large language models (LLMs), LLM inference cost has become a key challenge. Pruning techniques that introduce…
arXiv:2606.03631v3 Announce Type: replace Abstract: Multivariate time series classification (MTSC) is pivotal in high-stakes domains, such as clinical diagnosis and industrial fault detection, where safe deployment…
arXiv:2607.08785v1 Announce Type: new Abstract: High-quality data drives machine learning advances across industries. Recognizing the value of data, data transactions are increasingly common, giving rise to…
arXiv:2602.21196v2 Announce Type: replace Abstract: Efficiently processing long sequences with Transformer models usually requires splitting the computations across accelerators via context parallelism. The dominant approaches in…
arXiv:2607.08779v1 Announce Type: new Abstract: The signed integer alphabet contains one more negative representable value than positive. Yet, by convention, the standard symmetric integer quantizer fixes…
arXiv:2607.08780v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing…
arXiv:2607.08781v1 Announce Type: new Abstract: The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational…
arXiv:2607.08783v1 Announce Type: new Abstract: Manifold-valued measurements are prevalent in various machine learning tasks. Recent advances have extended Deep Neural Networks (DNNs) to operate on manifolds,…
arXiv:2607.08782v1 Announce Type: new Abstract: Expert parallelism has become the prevailing paradigm to serve Mixture-of-Experts (MoE) models. Its efficiency depends on the communication and computation latencies…
arXiv:2606.28225v2 Announce Type: replace Abstract: Temporal link prediction (TLP) is typically evaluated by predictive performance on unseen edges, but this criterion can conflate predictive accuracy with…
arXiv:2607.08784v1 Announce Type: new Abstract: Federated continual learning (FCL) evaluates how distributed clients learn from changing data streams while retaining previously learned knowledge. Existing evaluations are…
arXiv:2603.20388v2 Announce Type: replace-cross Abstract: We derive the asymptotic risk function of regularized empirical risk minimization (ERM) estimators tuned by $n$-fold cross-validation (CV). The out-of-sample prediction…