arXiv:2512.21521v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative training on decentralized data. Differential privacy (DP) is crucial for FL, but current private methods often rely on unrealistic assumptions (e.g., bounded gradients or heterogeneity), hindering practical application. Existing works…
arXiv:2507.02227v2 Announce Type: replace Abstract: Neural networks have emerged as powerful surrogates for solving partial differential equations (PDEs), offering significant computational speedups over traditional methods. However, these models suffer from a critical limitation: error accumulation during long-term rollouts, where small…
arXiv:2512.21527v1 Announce Type: new Abstract: Conventional Reinforcement Learning (RL) algorithms, typically focused on estimating or maximizing expected returns, face challenges when refining offline pretrained models with online experiences. This paper introduces Generative Actor Critic (GAC), a novel framework that decouples…
arXiv:2509.20896v2 Announce Type: replace Abstract: We propose a deterministic denoising algorithm for discrete-state diffusion models based on Markov chains. The generative reverse process is derandomized by introducing a variant of the herding algorithm with weakly chaotic dynamics, which induces deterministic…
arXiv:2512.21544v1 Announce Type: new Abstract: Accurate identification of antiviral peptides (AVPs) is critical for accelerating novel drug development. However, current computational methods struggle to capture intricate sequence dependencies and effectively handle ambiguous, hard-to-classify samples. To address these challenges, we propose…
arXiv:2511.08653v3 Announce Type: replace Abstract: Background: Recursive reasoning models achieve strong performance through iterative refinement, allowing small networks to match large language models. However, training is computationally expensive, often requiring 36 GPU-hours for Sudoku extreme. Existing models use fixed recursion…
arXiv:2512.21563v1 Announce Type: new Abstract: The design of novel algorithms for solving inverse problems in signal processing is an incredibly difficult, heuristic-driven, and time-consuming task. In this short paper, we the idea of automated algorithm discovery in the signal processing…
arXiv:2512.13710v2 Announce Type: replace Abstract: Flooding is one of the most destructive natural hazards worldwide, posing serious risks to ecosystems, infrastructure, and human livelihoods. This study combines Synthetic Aperture Radar (SAR) imagery with environmental and hydrological data to model flood…
arXiv:2512.21569v1 Announce Type: new Abstract: Spatio-temporal kriging is a fundamental problem in sensor networks, driven by the sparsity of deployed sensors and the resulting missing observations. Although recent approaches model spatial and temporal correlations, they often under-exploit two practical characteristics…
arXiv:2206.09132v2 Announce Type: replace-cross Abstract: In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k and can approach that of the JFT-300M dataset without the use of real…
