Technology ❯ Computer Science ❯ Artificial Intelligence

Machine Learning

Neural Networks Deep Learning Computer Vision Reinforcement Learning Federated Learning Model Optimization Natural Language Processing Model Training Performance Evaluation Large Language Models Model Evaluation Image Processing Retrieval-Augmented Generation Mixture-of-Experts Optimization Techniques Generative Models Performance Optimization Graph Neural Networks Machine Unlearning Optimization Evaluation Metrics Quantization Techniques Transformers Object Detection Multimodal Learning Knowledge Distillation Fine-Tuning Techniques Information Retrieval Low-Rank Adaptation Parameter-Efficient Fine-Tuning Mixture-of-Experts Models Continual Learning Image Retrieval Hyperparameter Tuning Transfer Learning Training Techniques Knowledge Transfer Retrieval Systems Personalized Learning Mixture of Experts Self-Distillation Video Processing Performance Improvement Domain Adaptation Frameworks In-Context Learning Performance Metrics Contrastive Learning Vision-Language Models 3D Modeling Representation Learning Recommendation Systems Algorithms Convolutional Neural Networks Data Privacy Policy Optimization Diffusion Models Model Architecture Security Parameter Efficiency Routing Algorithms Physics-Informed Neural Networks Language Models Unsupervised Learning Multi-task Learning Clustering Supervised Learning Association Rule Learning Neural Architecture Search Image Segmentation On-Policy Distillation Synthetic Data Vector Quantization Graph Retrieval Vision-Language Navigation Multimodal Retrieval Decentralized Learning Bias Amplification Temporal Data Analysis Research Papers Parameter-efficient Fine-tuning Data Fusion Data Processing Image Rendering Query Processing Algorithm Development Semantic Segmentation YOLO Framework Dense Retrieval Methods Data Distribution Model Control Fairness in Machine Learning Multilayer Perceptron Self-Supervised Learning Disentanglement Methods Parameter-Efficient Tuning Gradient Boosting Parameter-Efficient Methods Model Attacks Cost-sensitive Learning

Three Papers Offer Data, Inference and Safety Fixes for Fragile VLA Robot Models

The proposals aim to cut shortcut learning, stop open-loop action failures, and predict collisions before they occur.

MoE Research Delivers New Playbooks for Design, Routing, and Real-World Deployment

AI Learns the Flow of Time in Video

KumoRFM-2 Brings Plain-English Predictions to Enterprise Relational Data

HI-MoE Proposes Two-Stage Expert Routing for Object Detection

GPUBreach Rowhammer Attack Lets Unprivileged GPU Code Gain Root With IOMMU On

Sony Interactive Entertainment to Acquire UK Machine-Learning Startup Cinemersive Labs

Nvidia’s DLSS 5 Backlash Deepens After Conflicting Explanations of How It Works

DeepSeek Publishes mHC to Stabilize Wider Residual Streams in LLMs

VS-Graph Preprint Introduces Single-Pass Graph Learning That Rivals GNNs

New RAG Research Reports Adaptive Retrieval Gains, Multimodal Retrieval Edge

Apple Details ICCV 2025 Lineup With Eight Papers, Workshop Keynote, and Honolulu Exhibit

Studies Unveil Scaling Laws and Edge Quantization for Mixture-of-Experts Language Models

MIT’s AI-Printed Mask Restores Damaged Paintings in 3.5 Hours