Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.06798v2 Announce Type: replace-cross Abstract: Machine-learning emulators of chaotic and stochastic systems are usually validated on foreca…
arXiv:2610.06076v2 Announce Type: replace-cross Abstract: Preparing quantum states from classical data can cost more than the computation they serve;…
arXiv:2610.05922v2 Announce Type: replace-cross Abstract: Evaluating the causal effect of new features is a central goal for online platforms. While r…
arXiv:2610.04875v2 Announce Type: replace-cross Abstract: Diffusion large language models (DLLMs) generate text through iterative block denoising, and…
arXiv:2610.04801v2 Announce Type: replace-cross Abstract: A useful model of AI inference infrastructure must specify the system state, the information…
arXiv:2610.03025v2 Announce Type: replace-cross Abstract: What makes a short story gripping; a news article newsworthy; or a math proof elegant? These…
arXiv:2610.02687v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in enterprise, scientific, and medica…
arXiv:2608.09972v2 Announce Type: replace-cross Abstract: AI weather models are often reported to underestimate extremes, but most evidence concerns d…
arXiv:2608.07436v2 Announce Type: replace-cross Abstract: Muon-trained modular-arithmetic transformers can lose accuracy while retaining linearly deco…
arXiv:2607.17524v2 Announce Type: replace-cross Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that refr…
arXiv:2607.15271v2 Announce Type: replace-cross Abstract: Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off:…
arXiv:2606.16193v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-lang…
arXiv:2606.11570v2 Announce Type: replace-cross Abstract: We propose a spectral-based, unsupervised representation learning framework to derive low-di…
arXiv:2606.06840v2 Announce Type: replace-cross Abstract: Reasoning-trained language models can perform, zero-shot, multi-label tasks that require sel…
arXiv:2605.29695v2 Announce Type: replace-cross Abstract: Approximately 10% of newborns require assistance to initiate breathing at birth, and around…
arXiv:2605.28940v2 Announce Type: replace-cross Abstract: Recently observed empirical scaling laws describe the performance of foundation-type models…
arXiv:2605.17705v2 Announce Type: replace-cross Abstract: We study online conformal prediction in a partially observed panel: a new cross-section of p…
arXiv:2605.16578v4 Announce Type: replace-cross Abstract: Artificially generated speech is increasingly embedded in everyday life. Voice cloning in pa…
arXiv:2605.14285v3 Announce Type: replace-cross Abstract: Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, parti…
arXiv:2605.07079v2 Announce Type: replace-cross Abstract: World models predict future transitions from observations and actions. Existing works predom…