Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2409.14557v5 Announce Type: replace-cross Abstract: We study a structured class of Markov Decision Processes, known as Exo-MDPs, in which the st…
arXiv:2206.12041v3 Announce Type: replace-cross Abstract: The construction of most supervised learning datasets revolves around collecting multiple la…
arXiv:2608.12573v2 Announce Type: replace Abstract: Top-k selection is a fundamental computational primitive with applications spanning databases, inf…
arXiv:2607.16731v2 Announce Type: replace Abstract: Marine biogeochemical forecasting is increasingly important for managing marine ecosystems and the…
arXiv:2607.15682v3 Announce Type: replace Abstract: Learned dynamical proposals can generate configurations without providing a tractable endpoint den…
arXiv:2607.14895v2 Announce Type: replace Abstract: Reasoning language models (RLMs) demonstrate impressive performance by leveraging test-time comput…
arXiv:2607.05378v2 Announce Type: replace Abstract: Long-horizon agentic LLMs are increasingly limited by finite context windows, as extended interact…
arXiv:2607.04535v2 Announce Type: replace Abstract: Orthogonal and Stiefel layers give neural weights exact spectral control, but they also impose a s…
arXiv:2607.03651v3 Announce Type: replace Abstract: While traditional hub capacity planning models optimize effectively for quantitative inputs, they…
arXiv:2606.28228v2 Announce Type: replace Abstract: Causal representation learning for time series has developed strong identifiability results in dis…
arXiv:2606.27824v3 Announce Type: replace Abstract: Therapeutic peptides are a promising drug modality, but their generation must satisfy multiple the…
arXiv:2606.19138v2 Announce Type: replace Abstract: Neural Controlled Differential Equations (NCDE) provide a powerful continuous-time framework for f…
arXiv:2606.18967v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a representative post-training paradigm for large language…
arXiv:2606.15420v2 Announce Type: replace Abstract: Safety evaluations test a policy on prompts that omit the incentive information deployment supplie…
arXiv:2606.14597v2 Announce Type: replace Abstract: Transformer-based neural operators have shown remarkable performance for approximating solution op…
arXiv:2606.09030v2 Announce Type: replace Abstract: Clinical early warning systems built on irregularly sampled medical time series (ISMTS) from elect…
arXiv:2606.07631v2 Announce Type: replace Abstract: Emergent misalignment (EM) occurs when narrow finetuning induces dangerous behavior outside the fi…
arXiv:2606.01954v2 Announce Type: replace Abstract: Implicit-process priors define distributions over functions through flexible generative mechanisms…
arXiv:2606.00341v2 Announce Type: replace Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, de…
arXiv:2605.25819v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of s…