Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
arXiv:2508.18911v2 Announce Type: replace-cross Abstract: The primary goal of traditional federated learning is to protect data privacy by enabling distributed…
Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
arXiv:2508.19641v1 Announce Type: cross Abstract: Graph-structured data, which captures non-Euclidean relationships and interactions between entities, is growing in scale and…
Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery
arXiv:2508.17681v2 Announce Type: replace-cross Abstract: Bold claims about AI’s role in science-from “AGI will cure all diseases” to promises of…
pyFAST: A Modular PyTorch Framework for Time Series Modeling with Multi-source and Sparse Data
arXiv:2508.18891v1 Announce Type: cross Abstract: Modern time series analysis demands frameworks that are flexible, efficient, and extensible. However, many existing…
Interpretable Decision-Making for End-to-End Autonomous Driving
arXiv:2508.18898v1 Announce Type: cross Abstract: Trustworthy AI is mandatory for the broad deployment of autonomous vehicles. Although end-to-end approaches derive…
CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics
arXiv:2508.18124v2 Announce Type: replace-cross Abstract: We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed…
AI LLM Proof of Self-Consciousness and User-Specific Attractors
arXiv:2508.18302v1 Announce Type: new Abstract: Recent work frames LLM consciousness via utilitarian proxy benchmarks; we instead present an ontological and…
MedQARo: A Large-Scale Benchmark for Medical Question Answering in Romanian
arXiv:2508.16390v2 Announce Type: replace-cross Abstract: Question answering (QA) is an actively studied topic, being a core natural language processing (NLP)…
MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
arXiv:2508.17811v1 Announce Type: cross Abstract: Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction…
Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture
arXiv:2508.17814v1 Announce Type: cross Abstract: This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility…