arXiv:2603.03469v1 Announce Type: new Abstract: Generalization in generative modeling is defined as the ability to learn an underlying distribution from a finite dataset and produce novel samples, with evaluation largely driven by held-out performance and perceived sample quality. In practice, training is often stopped at the minimum of the test loss, taken as an operational indicator of generalization. We challenge this viewpoint by identifying a phase of biased generalization during training, in which the model continues to decrease […]

Ver mais

Detecting anomalies in link streams that represent various kinds of interactions is an important research topic with crucial applications. Because of the lack of ground truth data, proposed methods are mostly evaluated through their ability to detect randomly injected links. In contrast with most proposed methods, that rely on complex approaches raising computational and/or interpretability issues, we show here that trivial graph features and classical learning techniques are sufficient to detect such anomalies extremely well. This basic approach […]

Ver mais

Big data scenarios, where massive, heterogeneous datasets are distributed across clients, demand scalable, privacy-preserving learning methods. Federated learning (FL) enables decentralized training of machine learning (ML) models across clients without data centralization. Decentralized training, however, introduces a computational burden on client devices. U-shaped federated split learning (UFSL) offloads a fraction of the client computation to the server while keeping both data and labels on the clients’ side. However, the intermediate representations (i.e., smashed data) shared by clients with […]

Ver mais

arXiv:2603.23668v1 Announce Type: new Abstract: The rapid deployment of machine learning across platforms from milliwatt-class TinyML devices to large language models has made energy efficiency a primary constraint for sustainable AI. Across these scales, performance and energy are increasingly limited by data movement and memory-system behavior rather than by arithmetic throughput alone. This work reviews energy efficient software hardware codesign methods spanning edge inference and training to datacenter-scale LLM serving, covering accelerator architectures (e.g., ASIC/FPGA dataflows, processing-/compute-in-memory designs) […]

Ver mais

The Markup, now a part of CalMatters, uses investigative reporting, data analysis, and software engineering to challenge technology to serve the public good. Sign up for Klaxon, a newsletter that delivers our stories and tools directly to your inbox. The Markup won multiple awards of excellence in the Society for News Design’s Best of News Design Creative Competition, which honors excellence in visual storytelling, design, and journalism produced in 2023. “See the Neighborhoods Internet Providers Excluded from Fast […]

Ver mais

Sam Altman’s response to a recent New Yorker profile came at an unusually tense moment. His home was targeted in an attack a few days after the publication of a critical piece examining his leadership and influence. Altman framed both the incidents as part of a broader climate of intensifying discourse around artificial intelligence. Altman focused on the tone of the article’s specific claims rather than engaging with it directly. He also suggested that the way artificial intelligence […]

Ver mais

Graph-based techniques and spectral graph theory have enriched the field of machine learning with a variety of critical advances. A central object in the analysis is the graph Laplacian L, which encodes the structure of the graph. We consider the problem of learning over this Laplacian in a distributed streaming setting, where new edges of the graph are observed in real time by a network of workers. In this setting, it is hard to learn quickly or approximately […]

Ver mais

arXiv:2604.14167v1 Announce Type: new Abstract: Rhetoric recognition is a critical component in automated essay scoring. By identifying rhetorical elements in student writing, AI systems can better assess linguistic and higher-order thinking skills, making it an essential task in the area of AI for education. In this paper, we leverage Large Language Models (LLMs) for the Chinese rhetoric recognition task. Specifically, we explore Low-Rank Adaptation (LoRA) based fine-tuning and in-context learning to integrate rhetoric knowledge into LLMs. We formulate […]

Ver mais