Archives AI News

Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge

arXiv:2509.09955v1 Announce Type: new Abstract: Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive token merging, a novel mechanism that…

Learning Value of Information towards Joint Communication and Control in 6G V2X

arXiv:2505.06978v3 Announce Type: replace Abstract: As Cellular Vehicle-to-Everything (C-V2X) evolves towards future sixth-generation (6G) networks, Connected Autonomous Vehicles (CAVs) are emerging to become a key application. Leveraging data-driven Machine Learning (ML), especially Deep Reinforcement Learning (DRL), is expected to significantly…

SciML Agents: Write the Solver, Not the Solution

arXiv:2509.09936v1 Announce Type: new Abstract: Recent work in scientific machine learning aims to tackle scientific tasks directly by predicting target values with neural networks (e.g., physics-informed neural networks, neural ODEs, neural operators, etc.), but attaining high accuracy and robustness has…

Is Adversarial Training with Compressed Datasets Effective?

arXiv:2402.05675v3 Announce Type: replace Abstract: Dataset Condensation (DC) refers to the recent class of dataset compression methods that generate a smaller, synthetic, dataset from a larger dataset. This synthetic dataset aims to retain the essential information of the original dataset,…

Multi-Play Combinatorial Semi-Bandit Problem

arXiv:2509.09933v1 Announce Type: new Abstract: In the combinatorial semi-bandit (CSB) problem, a player selects an action from a combinatorial action set and observes feedback from the base arms included in the action. While CSB is widely applicable to combinatorial optimization…

Matrix-free Neural Preconditioner for the Dirac Operator in Lattice Gauge Theory

arXiv:2509.10378v1 Announce Type: cross Abstract: Linear systems arise in generating samples and in calculating observables in lattice quantum chromodynamics~(QCD). Solving the Hermitian positive definite systems, which are sparse but ill-conditioned, involves using iterative methods, such as Conjugate Gradient (CG), which…

Targeted Test Selection Approach in Continuous Integration

arXiv:2509.10279v1 Announce Type: cross Abstract: In modern software development change-based testing plays a crucial role. However, as codebases expand and test suites grow, efficiently managing the testing process becomes increasingly challenging, especially given the high frequency of daily code commits.…