Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.01028v1 Announce Type: new Abstract: Machine learning models often suffer performance degradation under subpopulation shift, particularly w…
arXiv:2610.00996v1 Announce Type: new Abstract: Reliable roll prediction of unmanned surface vehicles (USVs) is essential for ensuring navi?gational s…
arXiv:2610.00991v1 Announce Type: new Abstract: Majority voting over sampled completions is the workhorse of test-time scaling, and reinforcement lear…
arXiv:2610.00988v1 Announce Type: new Abstract: Cryptic ligand-binding pockets are not apparent in experimentally determined apo structures, making th…
arXiv:2610.00985v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) represent a compelling alternative to traditional Multi-Layer Percep…
arXiv:2610.00984v1 Announce Type: new Abstract: Accurate medication recommendation is central to clinical decision-making, directly determining therap…
arXiv:2610.00978v1 Announce Type: new Abstract: Time-series anomaly detection (TSAD) is difficult to generalize across datasets because heterogeneous…
arXiv:2610.00976v1 Announce Type: new Abstract: Probabilistic forecasting is important for predicting complex dynamical systems because intrinsic rand…
arXiv:2610.00968v1 Announce Type: new Abstract: Causal representation learning aims to discover robust features by exploiting the causal structure und…
arXiv:2610.00948v1 Announce Type: new Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are…
arXiv:2610.00929v1 Announce Type: new Abstract: Models specialized for the same task converge to similar behavior, yet the parameter updates that prod…
arXiv:2610.00927v1 Announce Type: new Abstract: We study episodic adversarial linear constrained Markov decision processes (CMDPs) with unknown transi…
arXiv:2610.00921v1 Announce Type: new Abstract: The cross-entropy method (CEM) uses world-model scores to select action sequences and fit the distribu…
arXiv:2610.00903v1 Announce Type: new Abstract: Test-time reinforcement learning (TTRL) adapts language models on unlabeled test problems using superv…
arXiv:2610.00898v1 Announce Type: new Abstract: Biological reasoning models use post-training to connect LLMs to biological foundation model represent…
arXiv:2610.00895v1 Announce Type: new Abstract: Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainab…
arXiv:2610.00894v1 Announce Type: new Abstract: Recent works on continuous diffusion for discrete data have demonstrated performance on par with compa…
arXiv:2610.00890v1 Announce Type: new Abstract: Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test o…
arXiv:2610.00888v1 Announce Type: new Abstract: Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the lang…
arXiv:2610.00873v1 Announce Type: new Abstract: In many industrial applications, 1) tabular data is scarce and imbalanced and thus requires synthetic…