createLiveAI LogocreateLiveAI
Page 112 of 130 • 1560 Total Articles

createLiveAI

Continue exploring the latest AI breakthroughs, technology insights, and industry analysis. Page 112 of our comprehensive AI news collection.

All Articles 1560 Business 249 Ethics 150 General 142 Policy 12 Research 793 Startups 13 Technology 201

📰 Latest Intelligence

Showing 12 articles on page 112 of 130

Live feed
arXiv Machine Learning
Research
EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge

Researchers have developed EmergentTTS-Eval, a new automated benchmark for evaluating TTS systems on complex and nuanced text scenarios, including emotions, foreign words, and complex pronunciations, by generating diverse test cases with LLMs. Using a Large Audio Language Model as a judge, the framework assesses multiple speech quality dimensions, revealing fine-grained performance differences among state-of-the-art TTS models and correlating well with human preferences.

GPT
Read More
arXiv Machine Learning
Research
Equivariant Spherical Transformer for Efficient Molecular Modeling - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

Equivariant Spherical Transformer for Efficient Molecular Modeling

The paper introduces the Equivariant Spherical Transformer (EST), a novel framework that enhances the expressiveness of SE(3)-equivariant Graph Neural Networks by integrating Transformer architecture within the Fourier-transformed group representation space. Empirical results on molecular benchmarks like OC20 and QM9 show that EST achieves state-of-the-art performance, overcoming limitations of previous tensor product-based convolutions.

Transformers
Read More
arXiv Machine Learning
Research
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference

The paper introduces FlashFormer, a specialized kernel designed to accelerate single-batch inference for transformer-based large language models, addressing the needs of low-batch, latency-sensitive applications like edge deployment. It demonstrates significant speedups over existing inference kernels across different model sizes and quantization settings, highlighting its potential for improving efficiency in real-world scenarios.

Transformers
Read More
arXiv Machine Learning
Research
FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification

A new method called Frequency Refined Augmentation (FreRA) enhances contrastive learning for time series classification by leveraging frequency domain analysis to preserve semantic information and improve data augmentation. Extensive experiments show that FreRA outperforms existing baselines across various datasets and tasks, demonstrating its effectiveness in contrastive representation learning and transfer learning scenarios.

Read More
arXiv Machine Learning
Research
From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data

This study demonstrates that fine-tuned Large EEG Models, specifically LaBraM, can accurately classify stress levels in real-world classroom settings, achieving a balanced accuracy of over 90%. The findings highlight the potential of LEMs to enhance brain-computer interfaces by effectively processing real-world EEG data beyond controlled clinical environments.

Read More
arXiv Machine Learning
Research
>- - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

>-

A new method called FSL-SAGE is proposed to improve federated split learning by estimating server gradients through auxiliary models, reducing communication costs and client memory needs while maintaining convergence rates comparable to FedAvg. This approach outperforms existing state-of-the-art methods in both efficiency and accuracy, addressing limitations of traditional federated and split learning techniques.

research machine-learning
Read More
arXiv Machine Learning
Research
Gradient Boosting Decision Tree with LSTM for Investment Prediction - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

Gradient Boosting Decision Tree with LSTM for Investment Prediction

A hybrid ensemble framework combining LSTM networks with LightGBM and CatBoost significantly enhances stock price prediction accuracy by 10-15% over individual models, effectively capturing market dynamics. The approach integrates multiple machine learning techniques and benchmarks performance across various metrics, demonstrating the potential of ensemble methods for financial forecasting.

research machine-learning
Read More
arXiv Machine Learning
Research
How Do Diffusion Models Improve Adversarial Robustness? - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

How Do Diffusion Models Improve Adversarial Robustness?

Recent research indicates that diffusion models can improve adversarial robustness, but the mechanisms are not fully understood. The study finds that diffusion-based purification increases the distance to clean samples and that robustness gains are linked to the model's input compression ability, with effectiveness varying under fixed randomness conditions.

Read More
arXiv Machine Learning
Research
Hybrid Cross-domain Robust Reinforcement Learning - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

Hybrid Cross-domain Robust Reinforcement Learning

The paper introduces HYDRO, a novel Hybrid Cross-Domain Robust RL framework that combines limited offline data with online simulation to improve policy robustness amid environment uncertainties. HYDRO employs uncertainty filtering and prioritized sampling to minimize performance gaps between simulators and real-world models, demonstrating superior sample efficiency and performance across various tasks.

Read More
arXiv Machine Learning
Research
Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations

This paper models message passing in graph neural networks as hyperbolic PDEs, creating a dynamical system that explicitly captures the graph's topological structure through eigenvector-based solution spaces. This approach enhances interpretability, aligns with spectral GNNs, and improves performance across various graph tasks by enabling explicit extraction of topological features.

Read More
arXiv Machine Learning
Research
Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition

The paper introduces PatchEchoClassifier, an energy-efficient model for human activity recognition using time-series sensor data, leveraging Echo State Networks and a tokenizer for patch-level features. It employs knowledge distillation from a high-capacity teacher, achieving over 80% accuracy with significantly lower computational costsabout one-sixth of DeepConvLSTMmaking it suitable for real-time edge applications.

Read More
arXiv Machine Learning
Research
Learning to Search for Vehicle Routing with Multiple Time Windows - AI news coverage from arXiv Machine Learning in Research
Research
📄 arXiv Machine Learning

Learning to Search for Vehicle Routing with Multiple Time Windows

Researchers developed RL-AVNS, a reinforcement learning-enhanced adaptive variable neighborhood search method for solving the Vehicle Routing Problem with Multiple Time Windows, outperforming traditional heuristics in solution quality and efficiency. The approach uses a transformer-based neural policy network to dynamically select neighborhood operators, demonstrating strong generalization to unseen instances and practical applicability in complex logistics scenarios.

Transformers
Read More
Previous Page
1 2 3 4 5 6 7 ... 130
Next Page

Page 112 of 130 • Showing articles 1333-1344 of 1560

Quick Navigation

Jump to any page or browse by category

Latest (Page 1) Business 249 Ethics 150 General 142 Policy 12 Research 793 Startups 13