Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.40090v1 Announce Type: cross Abstract: Particle transport under multiple scattering is central to radiative transfer and plasma physics, ye…
arXiv:2609.40087v1 Announce Type: cross Abstract: Flow-matching approaches to voice conversion (VC) have gained attention owing to their high speech q…
arXiv:2609.40085v1 Announce Type: cross Abstract: Echolocating bats can navigate dark and cluttered spaces using echolocation. Over a decade ago, BatS…
arXiv:2609.40077v1 Announce Type: cross Abstract: We study irrevocable maximum-cardinality matching in trees revealed by successive leaf attachments,…
arXiv:2609.40051v1 Announce Type: cross Abstract: Estimating causal effects from observational data is central to science and policy, but the effects…
arXiv:2609.40035v1 Announce Type: cross Abstract: The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy…
arXiv:2609.40027v1 Announce Type: cross Abstract: Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed…
arXiv:2609.40024v1 Announce Type: cross Abstract: We develop a general method for amortized Bayesian inference on multilevel models of arbitrary struc…
arXiv:2609.40016v1 Announce Type: cross Abstract: Exact incremental BPE maintains the canonical tokenization state after every appended byte. The rece…
arXiv:2609.40008v1 Announce Type: cross Abstract: Extracting the pion electromagnetic form factor $F_{\pi}(s)$ through phenomenological curve-fitting…
arXiv:2609.39971v1 Announce Type: cross Abstract: Vision-language-action (VLA) models can exceed 90% success on in-distribution tasks and withstand nu…
arXiv:2609.39957v1 Announce Type: cross Abstract: Coding agents solve repository-level tasks through sequences of actions, where a single erroneous ac…
arXiv:2609.39955v1 Announce Type: cross Abstract: Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reacti…
arXiv:2609.39933v1 Announce Type: cross Abstract: When designing machine learning models, desirable properties are often in tension: improving one beh…
arXiv:2609.39914v1 Announce Type: cross Abstract: Traditional simulations of parametric partial differential equations (PDEs) rely on repetitive compu…
arXiv:2609.39884v1 Announce Type: cross Abstract: Role prompting elicits specialized behavior from large language models through an expert identity, o…
arXiv:2609.39882v1 Announce Type: cross Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns asso…
arXiv:2609.39880v1 Announce Type: cross Abstract: Passwords remain the dominant online authentication mechanism, and understanding how humans choose t…
arXiv:2609.39869v1 Announce Type: cross Abstract: Grammar-constrained generation guarantees syntactic validity, but can substantially degrade semantic…
arXiv:2609.39868v1 Announce Type: cross Abstract: Exploratory reinforcement learning (RL) on an operating bus fleet is impractical,while policies trai…