Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.01670v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used as automated judges for instruction-b…
arXiv:2610.01662v1 Announce Type: cross Abstract: We establish complexity lower bounds for stochastic first-order algorithms in nonconvex--concave min…
arXiv:2610.01647v1 Announce Type: cross Abstract: In this article, we present our vision and recent advancements toward creating a decentralized syste…
arXiv:2610.01605v1 Announce Type: cross Abstract: Reliable visual reasoning requires composing multiple visual observations and returning consistent a…
arXiv:2610.01599v1 Announce Type: cross Abstract: Stochastic recursive momentum (STORM) achieves fast convergence for nonconvex optimization via the v…
arXiv:2610.01592v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly applied to process streaming data, with practitioners…
arXiv:2610.01583v1 Announce Type: cross Abstract: Despite many studies about causes and remedies of plasticity loss in Reinforcement Learning (RL) und…
arXiv:2610.01578v1 Announce Type: cross Abstract: Why can masked prediction learn useful representations that unmasked reconstruction misses? We study…
arXiv:2610.01572v1 Announce Type: cross Abstract: This paper investigates stochastic multi-level optimization where the objective is a nested composit…
arXiv:2610.01569v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive…
arXiv:2610.01560v1 Announce Type: cross Abstract: Model intelligence and fast response jointly shape the quality of interaction with speech language m…
arXiv:2610.01559v1 Announce Type: cross Abstract: World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to…
arXiv:2610.01546v1 Announce Type: cross Abstract: Primal-dual hybrid gradient (PDHG) methods solve large-scale linear programs (LPs) using GPU-friendl…
arXiv:2610.01533v1 Announce Type: cross Abstract: Existing work on Semantic IDs (SIDs) for generative recommendation treats SID construction as a repr…
arXiv:2610.01513v1 Announce Type: cross Abstract: Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: R…
arXiv:2610.01509v1 Announce Type: cross Abstract: An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLM…
arXiv:2610.01497v1 Announce Type: cross Abstract: Molecular tumor boards integrate genomic findings, clinical context, and therapeutic evidence to sup…
arXiv:2610.01472v1 Announce Type: cross Abstract: Comparing two high-dimensional discrete distributions has always been a challenging task due to the…
arXiv:2610.01468v1 Announce Type: cross Abstract: Low-cost NAS must both explore high-performing architectures and identify them reliably, yet reducin…
arXiv:2610.01432v1 Announce Type: cross Abstract: Simulating microstructure evolution requires quantum-mechanical accuracy and mesoscopic reach in len…