Federated learning (FL) is a popular distributed learning framework that trains a global model through iterative communications between a central server and edge devices. Recent works have demonstrated that FL is vulnerable to model poisoning attacks...
Supply chain attacks threaten open-source software ecosystems. This paper proposes a formal framework for quantifying trust in third-party software dependencies that is both formally checkable - formalized in satisfiability modulo theories (SMT) - wh...
This paper introduces a learning-based framework for robot adaptive manipulating the object with a revolute joint in unstructured environments. We concentrate our discussion on various cabinet door opening tasks. To improve the performance of Deep Re...
Tangent categories provide an axiomatic framework for understanding various tangent bundles and differential operations that occur in differential geometry, algebraic geometry, abstract homotopy theory, and computer science. Previous work has shown t...
In this paper, we explore how we can build upon the data and models of Internet images and use them to adapt to robot vision without requiring any extra labels. We present a framework called Self-supervised Embodied Active Learning (SEAL). It utilize...
Real-world Super-Resolution (Real-SR) methods focus on dealing with diverse real-world images and have attracted increasing attention in recent years. The key idea is to use a complex and high-order degradation model to mimic real-world degradations....
We investigate the relationship between Geometric Invariant Theory (GIT) heights and weighted heights, with a focus on their interaction in weighted projective spaces and their application to binary forms. Building on the weighted height framework de...
We present a novel framework that integrates Large Language Models (LLMs) into the Git bisect process for semantic fault localization. Traditional bisect assumes deterministic predicates and binary failure states assumptions often violated in modern...
Graphic design, which has been evolving since the 15th century, plays a crucial role in advertising. The creation of high-quality designs demands design-oriented planning, reasoning, and layer-wise generation. Unlike the recent CanvaGPT, which integr...
Recently we create so much data (2.5 quintillion bytes every day) that 90% of the data in the world today has been created in the last two years alone [1]. This data comes from sensors used to gather traffic or climate information, posts to social me...
I propose a unified framework for a joint analysis of the Drake equation and the Fermi paradox, which enables a simultaneous, quantitative study of both of them. The analysis is based on a simplified form of the Drake equation and on a fairly simple...
Resonance pole positions of the $f_0(500)$ alias $σ(500)$ meson are computed and plotted as a continuous function of pion mass in the framework of a unitary and analytic coupled-channel model for scalar mesons as dynamical $q\bar{q}$ states. The $σ...
Identifying druggable genes is essential for developing effective pharmaceuticals. With the availability of extensive, high-quality data, computational methods have become a significant asset. Protein Interaction Network (PIN) is valuable but challen...
Points: 353 | Comments: 199 | Author: Volker-E
The Riemann zeta function and the distribution of its nontrivial zeros on the critical line remain central topics in analytic number theory and large-scale computation. This work develops a numerical framework that replaces classical Gram-point brack...
Large ride-hailing platforms, such as DiDi, Uber and Lyft, connect tens of thousands of vehicles in a city to millions of ride demands throughout the day, providing great promises for improving transportation efficiency through the tasks of order dis...
Jan 20, 2025 · To run DeepSeek-R1 / R1-Zero, you'll need to install the open-source package llama.cpp, the original framework for using GGUF files. Hardware requirements: You do not need a GPU, a …
Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring genuine visual spatial reasoning. In this paper, we introduce a novel two-stage training framework designed to...
This paper takes the development of Central bank digital currencies as a perspective, introduces it into the Baumol-Tobin money demand theoretical framework, establishes the transactional money demand model under Central bank Digital Currency, and qu...
The purpose of this study is the design model of Islamic bank socialization in terms of four pillars (Business Institution, Formal Education, Islamic Scholar and Higher Education) through Synergy and Proactive. The location of the study was conducted...