arXiv:2509.05542v2 Announce Type: replace Abstract: Training multimodal process reward models (PRMs) is hard due to (i) distribution shift between training set and test set and (ii) quality imbalance across training data samples. While domain-level reweighting (e.g., DreamPRM) aligns training with…
arXiv:2504.08277v2 Announce Type: replace Abstract: Physics-informed neural operators offer a powerful framework for learning solution operators of partial differential equations (PDEs) by combining data and physics losses. However, these physics losses rely on derivatives. Computing these derivatives remains challenging, with…
arXiv:2506.03725v3 Announce Type: replace Abstract: Quite recently, large language models have made a significant breakthrough across various disciplines. However, training them is an extremely resource-intensive task, even for major players with vast computing resources. One of the methods gaining popularity…
arXiv:2510.18760v1 Announce Type: cross Abstract: Data restoration from degraded observations, of sparsity hypotheses, is an active field of study. Traditional iterative optimization methods are now complemented by deep learning techniques. The development of unfolded methods benefits from both families. We…
arXiv:2412.17231v2 Announce Type: replace Abstract: To bridge the digital divide, the space-ground integrated networks (SGINs), which will be a key component of the six-generation (6G) mobile networks, are expected to deliver artificial intelligence (AI) services to every corner of the…
arXiv:2505.15093v2 Announce Type: replace-cross Abstract: Protein fitness optimization involves finding a protein sequence that maximizes desired quantitative properties in a combinatorially large design space of possible sequences. Recent advances in steering protein generative models (e.g., diffusion models and language models)…
arXiv:2510.14222v2 Announce Type: replace-cross Abstract: In Machine Learning (ML), a regression algorithm aims to minimize a loss function based on data. An assessment method in this context seeks to quantify the discrepancy between the optimal response for an input-output system…
arXiv:2510.17898v1 Announce Type: new Abstract: The Mixture of Experts (MoE) architecture enables the scaling of Large Language Models (LLMs) to trillions of parameters by activating a sparse subset of weights for each input, maintaining constant computational cost during inference. Concurrently,…
arXiv:2510.17899v1 Announce Type: new Abstract: Automatic performance tuning (auto-tuning) is essential for optimizing high-performance applications, where vast and irregular parameter spaces make manual exploration infeasible. Traditionally, auto-tuning relies on well-established optimization algorithms such as evolutionary algorithms, annealing methods, or surrogate…
arXiv:2510.17895v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machine Unlearning has emerged as a promising solution, yet faces two key challenges:…
