📁 Frameworks

Plaud has launched a new app that records online meetings and offers a more comprehensive user experience.

A new framework has been introduced for evaluating the consistency-accuracy relation of LLMs under controlled input variations, using multiple-choice benchmarks as a case study. The framework proposes a global metric that combines the CAR curve to quantify the trade-off between accuracy and consistency.

A new framework for personalized search via agent-driven retrieval and knowledge-sharing

Nvidia's CUDA 13.1 introduces CUDA Tile, a new tile-centric programming path for AI model acceleration

L'industria dell'intelligenza artificiale sta affrontando nuove sfide con l'introduzione di sistemi AI autonomi. Per affrontare queste sfide, è stato sviluppato un nuovo framework di riferimento per governare i sistemi AI agenti.

Graph Neural Networks (GNNs) have emerged as a dominant paradigm for learning on graph-structured data, thanks to their ability to jointly exploit node features and relational information encoded in the graph topology. However, this joint modeling also introduces a critical weakness: perturbations or noise in either the structure or the features can be amplified through message passing, making GNNs highly vulnerable to adversarial attacks and spurious connections.

Meta has launched a new framework to improve the security of reward models in videos, reducing the risk of 'reward hacking'. The system, called SoliReward, uses a binary annotation strategy and a feature aggregation technique to provide more precise preference signals.

Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection

We propose a novel framework, termed Fourier-Activated Adapter (FAA), for parameter-efficient fine-tuning of large pre-trained language models.

Wireless Traffic Prediction with Large Language Model

A Reinforcement Learning Approach to Synthetic Data Generation

A new framework, DeepCQ, has been presented to predict the quality of compression. It offers a generalizable solution for various applications and compression technologies.

COMETH, a new framework, integrates probabilistic contextual learning with LLM-based semantics and human moral evaluations to model how context influences moral action perception.

LogicLens: a unified framework for Visual-Textual Co-reasoning that addresses the challenges of text-centric forgery analysis

Researchers have developed a new framework that combines AI with quantum physics to optimize 6G network management. The approach, called QI MARL, promises significant improvements in scalability and efficiency.

A new LLM-based platform measures rhetorical style independently of substantive content.

PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation

Synthetic data are widely used in the rapidly evolving field of Artificial Intelligence to accelerate innovation while preserving privacy and enabling broader data accessibility. However, the evaluation of synthetic data remains fragmented across heterogeneous metrics, ad-hoc scripts, and incomplete reporting practices.

A plain-text spaced repetition system for improved memory and learning. This article introduces the concept and discusses its practical applications.

Brave's preliminary browser has started testing its agent navigation, taking measures to ensure security and privacy.