arXiv:2602.04989v1 Announce Type: new Abstract: Online matching has been a mainstay in domains such as Internet advertising and organ allocation, but practical algorithms often lack strong theoretical guarantees. We take an important step toward addressing this by developing new online matching algorithms based on a coarsening approach. Although coarsening typically implies a loss of granularity, we show that, to the contrary, aggregating offline nodes into capacitated clusters can yield near-optimal theoretical guarantees. We apply our methodology to heart […]

Ver mais

Hi, I’ve been wanting to join the discord community of RL but I can’t find a valid invite link when searching on Google. Is anyone part of the community and can please send me an invite ? Thank you ! I’m looking forward to exchange more ! PS: If you also have any other links to other communities, like on Hugging Face, X or anything like that, please let me know. I find it interesting to read as […]

Ver mais

arXiv:2601.16990v1 Announce Type: new Abstract: Bibliometric analysis is a critical tool for understanding the structure, dynamics, and impact of scientific research. Traditional methods often fall short in capturing the intricate relationships and evolving trends within scientific literature. To address this gap, we present pyBiblioNet, a Python library designed to facilitate comprehensive network-based bibliometric analysis, providing insights into citation networks, co-authorship networks, and keyword co-occurrence networks. The library integrates with OpenAlex, a popular and open catalogue to the global […]

Ver mais

We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level, CRAFT aligns large reasoning models to generate safety-aware reasoning traces by explicitly optimizing objectives defined over the hidden state space. Methodologically, CRAFT integrates contrastive representation learning with reinforcement learning to separate safe and unsafe reasoning trajectories, yielding a latent-space geometry that supports robust, reasoning-level safety alignment. Theoretically, […]

Ver mais

arXiv:2606.07914v1 Announce Type: new Abstract: We study component recovery and mixing-matrix estimation from unlabeled finite mixtures whose observable distributions share the same latent components but have unknown mixing weights. The main identifying signal is marginal independence: each component is assumed to be independent on at least one coordinate pair, but no labels, clean component samples, or mixing weights are observed. We first prove a structural result for product components: under linear independence of the univariate marginals, any independent […]

Ver mais

Symbolic discovery of governing equations is a long-standing goal in scientific machine learning, yet a fundamental trade-off persists between interpretability and scalable learning. Classical symbolic regression methods yield explicit analytic expressions but rely on combinatorial search, whereas neural networks scale efficiently with data and dimensionality but produce opaque representations. In this work, we introduce Symbolic Kolmogorov-Arnold Networks (Symbolic-KANs), a neural architecture that bridges this gap by embedding discrete symbolic structure directly within a trainable deep network. Symbolic-KANs represent […]

Ver mais

Introduction Throughout my academic career, I worked on various problems surrounding the robustness of deep learning models. Until a few years ago, these topics had their own niches within the academic but also industrial community. While some of this work got adopted in specific domains, e.g., consider corruption robustness benchmarks such as ImageNet-C in computer vision, much of it stayed separate from more mainstream developments such as foundation models. Today, in contrast, work on evaluation metrics and benchmarks […]

Ver mais

arXiv:2601.01055v1 Announce Type: new Abstract: This paper develops the algorithmic and dynamical foundations of recursive ensemble learning driven by Fibonacci-type update flows. In contrast with classical boosting Freund and Schapire (1997); Friedman (2001), where the ensemble evolves through first-order additive updates, we study second-order recursive architectures in which each predictor depends on its two immediate predecessors. These Fibonacci flows induce a learning dynamic with memory, allowing ensembles to integrate past structure while adapting to new residual information. We […]

Ver mais

arXiv:2602.06195v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference labels presents a severe cost and scalability bottleneck. To overcome this, We propose a semi-supervised framework augmenting limited human data with a large corpus of unlabeled pairs annotated via cost-effective synthetic AI feedback. Our paper introduces Debiased DPO (DeDPO), which uniquely integrates a debiased […]

Ver mais