Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2512.13708v2 Announce Type: replace Abstract: Inferring interaction structure from steady-state observations is a central inverse problem when t…
arXiv:2512.03579v2 Announce Type: replace Abstract: Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frame…
arXiv:2512.01917v2 Announce Type: replace Abstract: Eddy-covariance (EC) flux towers provide in situ measurements of $CO_2$ flux and serve as the grou…
arXiv:2511.21075v4 Announce Type: replace Abstract: Engineering LLMs to accelerate life sciences research requires a robust alignment with biomedical…
arXiv:2511.20718v3 Announce Type: replace Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large languag…
arXiv:2511.11500v3 Announce Type: replace Abstract: Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when no…
arXiv:2511.00053v2 Announce Type: replace Abstract: The design of learning objectives is central to training time-series forecasting models. Existing…
arXiv:2511.00044v4 Announce Type: replace Abstract: Physical neural networks (PNNs) are promising candidates for next-generation computing, but existi…
arXiv:2510.24574v3 Announce Type: replace Abstract: Training time-series forecasting models requires aligning the conditional distribution of model fo…
arXiv:2510.14878v3 Announce Type: replace Abstract: We study kernel regression with common rotation-invariant kernels on real datasets including CIFAR…
arXiv:2510.01264v2 Announce Type: replace Abstract: Progress in adversarial multi-agent reinforcement learning (MARL) for robotics has been hampered b…
arXiv:2509.18169v4 Announce Type: replace Abstract: Tasks on complex systems require high-precision numerical computation to support decisions. Howeve…
arXiv:2508.14748v2 Announce Type: replace Abstract: The increasing variety of molecular data creates a need for generative models that can flexibly in…
arXiv:2507.06529v2 Announce Type: replace Abstract: Bayesian optimization (BO) is a powerful paradigm for optimizing expensive black-box functions. Tr…
arXiv:2505.17847v3 Announce Type: replace Abstract: Training time-series forecasting models poses unique challenges in loss function design. Most exis…
arXiv:2505.14777v2 Announce Type: replace Abstract: The design of effective optimization algorithms for neural networks remains a fundamental challeng…
arXiv:2502.19741v4 Announce Type: replace Abstract: Estimating causal effects under networked interference from observational data is a crucial yet ch…
arXiv:2409.09984v2 Announce Type: replace Abstract: The sharpness-aware minimization (SAM) algorithm and its variants, including gap guided SAM (GSAM)…
arXiv:2402.02399v3 Announce Type: replace Abstract: Time series modeling presents unique challenges due to autocorrelation in both historical data and…
arXiv:2401.09918v2 Announce Type: replace Abstract: Rule set learning has recently been frequently revisited because of its interpretability. Existing…