arXiv:2602.17801v1 Announce Type: new Abstract: A Euclidean noncrossing Steiner $(1+epsilon)$-spanner for a point set $Psubsetmathbb{R}^2$ is a planar straight-line graph that, for any two points $a, b in P$, contains a path whose length is at most $1+epsilon$ times the Euclidean distance between $a$ and $b$. We construct a Euclidean noncrossing Steiner $(1+epsilon)$-spanner with $O(n/epsilon^{3/2})$ edges for any set of $n$ points in the plane. This result improves upon the previous best upper bound of $O(n/epsilon^{4})$ obtained nearly […]

Ver mais

arXiv:2602.17726v1 Announce Type: new Abstract: In January 2026, torrential rains killed 200-300 people across Southern Africa, exposing a critical reality: 60% of the continent lacks effective early warning systems due to infrastructure costs. Traditional radar stations exceed USD 1 million each, leaving Africa with an 18x coverage deficit compared to the US and EU. We present a production-grade architecture for deploying NVIDIA Earth-2 AI weather models at USD 1,430-1,730/month for national-scale deployment – enabling coverage at 2,000-4,545x lower […]

Ver mais

Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent research suggests that structural collapse leads to loss of plasticity, as evidenced by changes in effective rank (eRank). This indicates a link to forgetting, since the networks lose the ability to expand their feature space to learn new tasks, which forces the network to overwrite […]

Ver mais

arXiv:2606.00157v1 Announce Type: new Abstract: We consider establishing the interpretability theory of deep learning through constructing a corresponding relationship between the renormalization group (RG) method in statistical physics and the training process of deep neural networks (DNNs). We have proved the constructed relationship using the one-dimensional Ising model as the input data. In this paper we generalize our results to the case of continuous input data, which is a necessary preparation for applying the corresponding framework to real-world […]

Ver mais

arXiv:2602.12322v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging in open-world environments. We present Visual Foresight Planning (ForeAct), a general and efficient planner that guides a VLA step-by-step using imagined future observations and subtask descriptions. With an imagined future observation, the VLA can focus on visuo-motor inference rather than high-level semantic reasoning, leading to improved accuracy and generalization. Our planner comprises a highly efficient foresight […]

Ver mais

arXiv:2604.07390v1 Announce Type: new Abstract: The aggressive densification of modern wireless networks necessitates judicious resource allocation to mitigate severe mutual interference. However, classical iterative algorithms remain computationally prohibitive for real-time applications requiring rapid responsiveness. While recent deep learning-based methods show promise, they typically function as task-specific solvers lacking the flexibility to adapt to different objectives and scenarios without expensive retraining. To address these limitations, we propose a graph foundation model for resource allocation (GFM-RA) based on a pre-training […]

Ver mais

arXiv:2601.21868v1 Announce Type: new Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning. This paper provides quantitative bounds on the sampling error of score-based generative models by leveraging stability and forgetting properties of the Markov chain associated with the reverse-time dynamics. Under weak assumptions, we provide the two structural properties to ensure the propagation of initialization and discretization errors of the backward process: a Lyapunov drift condition and a […]

Ver mais

Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However, purely symbolic architectures are complex to scale and difficult to apply to continuous settings. Hence, we propose a hybrid approach, inspired by humans’ ability to acquire new skills. We use a two-stage framework that injects symbolic structure into neural-based reinforcement learning agents without sacrificing the expressivity of deep […]

Ver mais

arXiv:2601.12134v1 Announce Type: new Abstract: As AI assistance becomes embedded in programming practice, researchers have increasingly examined how these systems help learners generate code and work more efficiently. However, these studies often position AI as a replacement for human collaboration and overlook the social and learning-oriented aspects that emerge in collaborative programming. Our work introduces human-human-AI (HHAI) triadic programming, where an AI agent serves as an additional collaborator rather than a substitute for a human partner. Through a […]

Ver mais