Many complex networks have partially observed or evolving connectivity, making link prediction a fundamental task. Topological link prediction infers missing links using only network topology, with applications in social, biological, and technological systems. The Cannistraci-Hebb (CH) theory provides a topological formulation of Hebbian learning, grounded on two pillars: (1) the minimization of external links within local communities, and (2) the path-based definition of local communities that capture homophilic (similarity-driven) interactions via paths of length 2 and synergetic (diversitydriven) […]

Ver mais

arXiv:2312.16819v4 Announce Type: replace-cross Abstract: We consider the optimization problem associated with training two-layer ReLU networks with (d) inputs under the squared loss, where the labels are generated by a target network. Recent work has identified two distinct classes of infinite families of minima: one whose training loss vanishes in the high-dimensional limit, and another whose loss remains bounded away from zero. The latter family is empirically avoided by stochastic gradient descent, hence emph{hidden}, motivating the search for […]

Ver mais

arXiv:2601.04227v1 Announce Type: new Abstract: Generative audio technologies now enable highly realistic voice cloning and real-time voice conversion, increasing the risk of impersonation, fraud, and misinformation in communication channels such as phone and video calls. This study investigates real-time detection of AI-generated speech produced using Retrieval-based Voice Conversion (RVC), evaluated on the DEEP-VOICE dataset, which includes authentic and voice-converted speech samples from multiple well-known speakers. To simulate realistic conditions, deepfake generation is applied to isolated vocal components, followed […]

Ver mais

arXiv:2507.22095v4 Announce Type: replace Abstract: We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in Lee et al. 2023, to address limitations of the standard Gaussian prior. It has been proved in Lee et al. 2023 that, as the number of nodes in the hidden layers grows large, according to a sequential and ordered limit, the law of the output converges weakly to a Gaussian mixture. Among our results, we […]

Ver mais

arXiv:2601.17020v1 Announce Type: new Abstract: With the rising popularity of interdisciplinary work and increasing institutional incentives in this direction, there is a growing need to understand how resulting publications incorporate ideas from multiple disciplines. Existing computational approaches, such as affiliation diversity, keywords, and citation patterns, do not account for how individual citations are used to advance the citing work. Although, in line with addressing this gap, prior studies have proposed taxonomies to classify citation purpose, these frameworks are […]

Ver mais

Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to backdoor attacks. Existing attack strategies typically struggle against safety-constrained algorithms (e.g., CQL) due to inefficient random poisoning and the use of easily detectable Out-of-Distribution (OOD) triggers. In this paper, we propose CS-GBA (Critical Sample-based Gradient-guided Backdoor Attack), a novel framework designed to achieve high stealthiness and destructiveness under a strict budget. Leveraging the theoretical insight that samples with high Temporal Difference (TD) errors […]

Ver mais

Due to their adaptability and mobility, Unmanned Aerial Vehicles (UAVs) are becoming increasingly essential for wireless network services, particularly for data harvesting tasks. In this context, Artificial Intelligence (AI)-based approaches have gained significant attention for addressing UAV path planning tasks in large and complex environments, bridging the gap with real-world deployments. However, many existing algorithms suffer from limited training data, which hampers their performance in highly dynamic environments. Moreover, they often overlook the inherently multi-objective nature of the […]

Ver mais

arXiv:2601.15380v1 Announce Type: cross Abstract: We generalize the attention mechanism by viewing it through the lens of Entropic Optimal Transport, revealing that standard attention corresponds to a transport problem regularized by an implicit uniform prior. We introduce Generalized Optimal transport Attention with Trainable priors (GOAT), a new attention mechanism that replaces this naive assumption with a learnable, continuous prior. This prior maintains full compatibility with optimized kernels such as FlashAttention. GOAT also provides an EOT-based explanation of attention […]

Ver mais

Hey yall, I started working on this https://github.com/jimmie-jams/SilksongRL a while ago and finally managed to train an agent to beat one (1) boss. So, I figured it was time to share my glorious creation with the world. Jokes aside, I’d love to hear your thoughts! There are more environments/bosses already configured and it’s very easy to add new ones as well but I just don’t have the time/compute to train agents at a faster rate than I currently […]

Ver mais

Large language models (LLMs) offer one of the most interesting opportunities for developing more efficient training methods. A few weeks ago, the NeurIPS 2023 LLM Efficiency Challenge launched to focus on efficient LLM finetuning, and this guide is a short walkthrough explaining how to participate in this competition. This article covers everything you need to know, from setting up the coding environment to making the first submission.

Ver mais