Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.00607v1 Announce Type: cross Abstract: Historical music restoration (HMR) has almost exclusively focused on constrained problems such as Su…
arXiv:2610.00596v1 Announce Type: cross Abstract: In frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems, the upl…
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical…
arXiv:2610.00569v1 Announce Type: cross Abstract: Full detector simulation and reconstruction of collider events are projected to become major bottlen…
arXiv:2610.00562v1 Announce Type: cross Abstract: Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate rele…
arXiv:2610.00546v1 Announce Type: cross Abstract: Exact stochastic equations for non-equilibrium dynamics are rarely accessible. We show that the long…
arXiv:2610.00535v1 Announce Type: cross Abstract: Uncertainty quantification is critical in scientific machine learning, where black-box, image-based…
arXiv:2610.00524v1 Announce Type: cross Abstract: Vision-language-action (VLA) models often struggle to generalize to skill combinations absent from t…
arXiv:2610.00515v1 Announce Type: cross Abstract: Neural operators learn maps between function spaces, while hereditary network dynamics are described…
arXiv:2610.00498v1 Announce Type: cross Abstract: When minimizing the squared-error loss, the popular CP decomposition can be interpreted as parameter…
arXiv:2610.00487v1 Announce Type: cross Abstract: Autonomously constructing physically realizable 3D structures remains a significant challenge due to…
arXiv:2610.00465v1 Announce Type: cross Abstract: Next-generation large language models (LLMs) are expanding from the cloud to ubiquitous edge devices…
arXiv:2610.00451v1 Announce Type: cross Abstract: Human motion, environmental contacts, and interaction forces are governed by common physical laws, y…
arXiv:2610.00431v1 Announce Type: cross Abstract: Continual parameter-efficient fine-tuning for large language models (LLMs) must balance retention of…
arXiv:2610.00424v1 Announce Type: cross Abstract: Knowing how much a causal predictor could improve need not reveal the gain of the repair actually le…
arXiv:2610.00422v1 Announce Type: cross Abstract: Neural combinatorial optimization typically assumes a centralized solver that reads the whole instan…
arXiv:2610.00420v1 Announce Type: cross Abstract: A weight space network (or metanetwork) takes the weights of another neural network as input and pre…
arXiv:2610.00416v1 Announce Type: cross Abstract: Evaluating large language models becomes increasingly challenging as their capabilities advance: ben…
arXiv:2610.00382v1 Announce Type: cross Abstract: Model quantization reduces the numerical precision of neural network weights and activations to lowe…
arXiv:2610.00348v1 Announce Type: cross Abstract: Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted…