arXiv:2510.03251v1 Announce Type: new Abstract: Many methods aim to enhance time series forecasting by decomposing the series through intricate model structures and prior knowledge, yet they are inevitably limited by computational complexity and the robustness of the assumptions. Our research…
arXiv:2510.03252v1 Announce Type: new Abstract: Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligned tuples or can only handle domain pairs seen in training, limiting their practicality and excluding many cross-domain mappings.…
arXiv:2510.03248v1 Announce Type: new Abstract: Traumatic brain injury (TBI) remains a major public health concern, with over 69 million cases annually worldwide. Finite element (FE) models offer high-fidelity predictions of brain deformation but are computationally expensive, requiring hours per simulation…
arXiv:2510.03250v1 Announce Type: new Abstract: Differentiable logic gate networks (DLGNs) exhibit extraordinary efficiency at inference while sustaining competitive accuracy. But vanishing gradients, discretization errors, and high training cost impede scaling these networks. Even with dedicated parameter initialization schemes from subsequent…
arXiv:2510.03247v1 Announce Type: new Abstract: Active learning (AL) is a principled strategy to reduce annotation cost in data-hungry deep learning. However, existing AL algorithms focus almost exclusively on unimodal data, overlooking the substantial annotation burden in multimodal learning. We introduce…
arXiv:2510.03246v1 Announce Type: new Abstract: Pruning is critical for scaling large language models (LLMs). Global pruning achieves strong performance but requires $mathcal{O}(N)$ memory, which is infeasible for billion-parameter models. Local pruning reduces GPU memory usage to that of a single…
arXiv:2510.03245v1 Announce Type: new Abstract: Ensuring the reliability of deep neural networks (DNNs) in the presence of real world noise and intentional perturbations remains a significant challenge. To address this, attribution methods have been proposed, though their efficacy remains suboptimal…
arXiv:2505.23614v2 Announce Type: replace Abstract: Classical search algorithms have long underpinned modern artificial intelligence. In this work, we tackle the challenge of inference-time control in diffusion models — adapting generated outputs to meet diverse test-time objectives — using principles from…
arXiv:2510.03253v1 Announce Type: new Abstract: Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems. Aligning these agents via preference-based offline methods like Direct Preference Optimization (DPO) is a promising direction, yet it faces a…
arXiv:2510.03254v1 Announce Type: new Abstract: Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as spam email filtering, malware detection and fake image generation, where security methods must be actively…
