Latest AI/ML News

9894 articles · arXiv cs.LG

arXiv cs.LGOct 2, 2026

arXiv:2610.00405v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series…

arXiv cs.LGOct 2, 2026

arXiv:2610.00403v1 Announce Type: new Abstract: A network can fit its training examples while failing to recover the rule that generated their labels.…

arXiv cs.LGOct 2, 2026

arXiv:2610.00400v1 Announce Type: new Abstract: Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcom…

arXiv cs.LGOct 2, 2026

arXiv:2610.00399v1 Announce Type: new Abstract: Metacognition involves reasoning about cognitive processes themselves. An example is in resource alloc…

arXiv cs.LGOct 2, 2026

arXiv:2610.00398v1 Announce Type: new Abstract: Overnight impedance pneumography (IP) is used to monitor paediatric respiratory health. Its current cl…

arXiv cs.LGOct 2, 2026

arXiv:2610.00397v1 Announce Type: new Abstract: Identifying which speaker a listener is attending to in a noisy room -- the cocktail-party problem --…

arXiv cs.LGOct 2, 2026

arXiv:2610.00395v1 Announce Type: new Abstract: Inference-time steering enables pretrained diffusion models to satisfy new constraints without full re…

arXiv cs.LGOct 2, 2026

arXiv:2610.00394v1 Announce Type: new Abstract: This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data re…

arXiv cs.LGOct 2, 2026

arXiv:2610.00391v1 Announce Type: new Abstract: Synthetic medical tabular data generation has become essential for developing and validating computer-…

arXiv cs.LGOct 2, 2026

arXiv:2610.00389v1 Announce Type: new Abstract: Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism.…

arXiv cs.LGOct 2, 2026

arXiv:2610.00388v1 Announce Type: new Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through…

arXiv cs.LGOct 2, 2026

arXiv:2610.00385v1 Announce Type: new Abstract: Replay selectors often rank cached trajectories by format feedback, confidence, freshness, or response…

arXiv cs.LGOct 2, 2026

arXiv:2610.00383v1 Announce Type: new Abstract: Modern text-to-image (T2I) systems can be improved without modifying generator parameters by adapting…

arXiv cs.LGOct 2, 2026

arXiv:2610.00381v1 Announce Type: new Abstract: Medical models are judged not only on correctness, but on whether reported confidence matches actual a…

arXiv cs.LGOct 2, 2026

arXiv:2610.00380v1 Announce Type: new Abstract: Depression is a mental condition that can lead to suicide and self-harm. Predicting the outcome of dep…

arXiv cs.LGOct 2, 2026

arXiv:2610.00377v1 Announce Type: new Abstract: Station-based weather forecasting supports daily life and economic activity, yet accurate forecasts re…

arXiv cs.LGOct 2, 2026

arXiv:2610.00376v1 Announce Type: new Abstract: We evaluate Jev on ten dataset-defined application labels in CESNET-QUICEXT-25 using only the first te…

arXiv cs.LGOct 2, 2026

arXiv:2610.00373v1 Announce Type: new Abstract: Attention-head ablation, zeroing a head and measuring the resulting change in task performance, is a c…

arXiv cs.LGOct 2, 2026

arXiv:2610.00370v1 Announce Type: new Abstract: Station weather forecasting is fundamentally shaped by both complex spatial dependencies across statio…

arXiv cs.LGOct 2, 2026

arXiv:2610.00367v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models enable parameter scaling with limited per-token computation by activat…

← PreviousPage 49 of 495Next →