Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.39277v1 Announce Type: new Abstract: Looped models reason by applying the same block of weights many times, so compressing that block saves…
arXiv:2609.39275v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher f…
arXiv:2609.39271v1 Announce Type: new Abstract: Manifold-valued data, and consequently the distributions they induce, are prevalent across many domain…
arXiv:2609.39268v1 Announce Type: new Abstract: Irregular time series, characterized by non-uniform sampling intervals, missing observations, and vari…
arXiv:2609.39261v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictors through downstream objectives, but a different loss…
arXiv:2609.39257v1 Announce Type: new Abstract: Accurate forecasting of electricity production is essential for maintaining the operational efficiency…
arXiv:2609.39250v1 Announce Type: new Abstract: Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by e…
arXiv:2609.39247v1 Announce Type: new Abstract: Standard language model RL algorithms credit every token of a long rollout with the same advantage det…
arXiv:2609.39243v1 Announce Type: new Abstract: Causal interventions such as activation patching and distributed alignment search (DAS) are the main t…
arXiv:2609.39242v1 Announce Type: new Abstract: Persistent homology can be differentiated and incorporated into learning pipelines, but no analogous f…
arXiv:2609.39232v1 Announce Type: new Abstract: EDF relies on continuous monitoring of its power plants to detect anomalies as soon as they occur. Giv…
arXiv:2609.39223v1 Announce Type: new Abstract: Large language model (LLM) inference is increasingly moving toward lower precision to realize the thro…
arXiv:2609.39215v1 Announce Type: new Abstract: Time series anomaly detection (TSAD) is increasingly deployed in streaming settings, where data arrive…
arXiv:2609.39194v1 Announce Type: new Abstract: Wireless split learning (SL) reduces on-device computation by offloading upper layers to a server, yet…
arXiv:2609.39190v1 Announce Type: new Abstract: A deep classifier is defined not only by the decision it produces, but also by the sequence of transfo…
arXiv:2609.39188v1 Announce Type: new Abstract: Developmental psychology holds that certain priors are given to infants prior to experience rather tha…
arXiv:2609.39185v1 Announce Type: new Abstract: Mamba-style and hybrid language models compress their past into a fixed-size recurrent state that is r…
arXiv:2609.39177v1 Announce Type: new Abstract: Deep neural networks tend to rely on simple features that may be spurious and thus fail to generalize.…
arXiv:2609.39164v1 Announce Type: new Abstract: Score-based variational inference (VI) provides an alternative to Kullback--Leibler (KL)-based VI by m…
arXiv:2609.39144v1 Announce Type: new Abstract: We prove a sharp Gaussian approximation for the invariant law of constant-stepsize SGD with bounded ad…