Latest AI/ML News

9894 articles · arXiv cs.LG

arXiv cs.LGOct 2, 2026

arXiv:2607.06320v3 Announce Type: replace-cross Abstract: We present the dithered Gaussian mechanism, an alternative to the discrete Gaussian mechanis…

arXiv cs.LGOct 2, 2026

arXiv:2607.04513v2 Announce Type: replace-cross Abstract: Flow matching is a powerful tool for generative modeling, but emerging applications in robot…

arXiv cs.LGOct 2, 2026

arXiv:2607.04162v2 Announce Type: replace-cross Abstract: General-purpose manipulation requires both semantic reasoning over task constraints and reli…

arXiv cs.LGOct 2, 2026

arXiv:2607.03502v2 Announce Type: replace-cross Abstract: Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or…

arXiv cs.LGOct 2, 2026

arXiv:2606.21562v2 Announce Type: replace-cross Abstract: Transformers are AI's workhorse but their computational cost becomes prohibitive when proces…

arXiv cs.LGOct 2, 2026

arXiv:2606.17710v3 Announce Type: replace-cross Abstract: Vision-language models that answer questions about chest radiographs are evaluated by their…

arXiv cs.LGOct 2, 2026

arXiv:2606.05363v3 Announce Type: replace-cross Abstract: On a platform with many sellers, should a pricing algorithm explicitly model competitors' pr…

arXiv cs.LGOct 2, 2026

arXiv:2605.28009v2 Announce Type: replace-cross Abstract: Memory-augmented large language models extend reasoning beyond a fixed context window by mai…

arXiv cs.LGOct 2, 2026

arXiv:2605.22875v2 Announce Type: replace-cross Abstract: Long-horizon mathematical reasoning fails less often because a model cannot produce a valid…

arXiv cs.LGOct 2, 2026

arXiv:2605.20531v3 Announce Type: replace-cross Abstract: Reliable verification of proofs remains a bottleneck for training and evaluating AI systems…

arXiv cs.LGOct 2, 2026

arXiv:2605.13570v2 Announce Type: replace-cross Abstract: Constraint-based game content generators that learn local constraints from existing content,…

arXiv cs.LGOct 2, 2026

arXiv:2605.12491v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all sel…

arXiv cs.LGOct 2, 2026

arXiv:2605.08172v2 Announce Type: replace-cross Abstract: Anatomical mesh segmentation requires models that operate directly on irregular surface geom…

arXiv cs.LGOct 2, 2026

arXiv:2604.26766v2 Announce Type: replace-cross Abstract: Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent chall…

arXiv cs.LGOct 2, 2026

arXiv:2604.18572v3 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis posits that neural networks trained on different moda…

arXiv cs.LGOct 2, 2026

arXiv:2604.13179v2 Announce Type: replace-cross Abstract: This paper presents HUANet, a constrained deep neural network architecture that unrolls the…

arXiv cs.LGOct 2, 2026

arXiv:2604.12905v2 Announce Type: replace-cross Abstract: Force and torque (F/T) sensors enable contact-aware control by providing reactive feedback,…

arXiv cs.LGOct 2, 2026

arXiv:2604.12102v3 Announce Type: replace-cross Abstract: We describe compute-grounded reasoning (CGR), a design pattern in which code computes select…

arXiv cs.LGOct 2, 2026

arXiv:2604.07639v2 Announce Type: replace-cross Abstract: Broadly applicable quantum advantage, particularly in classical data processing and machine…

arXiv cs.LGOct 2, 2026

arXiv:2604.05518v2 Announce Type: replace-cross Abstract: We propose an active learning algorithm for linear system identification with optimal center…

← PreviousPage 25 of 495Next →