84 articles tagged with #self-supervised-learning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce SVG, a new latent diffusion model that eliminates the need for variational autoencoders by using self-supervised representations. The approach leverages frozen DINO features to create semantically structured latent spaces, enabling faster training, fewer sampling steps, and better generative quality while maintaining semantic capabilities.
Researchers have developed a self-supervised learning method that can reconstruct audio and images from clipped/saturated measurements without requiring ground truth training data. The approach extends self-supervised learning to non-linear inverse problems and performs nearly as well as fully supervised methods while using only clipped measurements for training.
Researchers developed a behavioral benchmark showing that self-supervised vision transformers, particularly those trained with DINO objectives, align closely with human object perception and segmentation behavior. The study found that models with stronger object-centric representations better predict human visual judgments, with Gram matrix structure playing a key role in perceptual alignment.
Researchers propose directional CDNV (decision-axis variance) as a key geometric quantity explaining why self-supervised learning representations transfer well with few labels. The study shows that small variability along class-separating directions enables strong few-shot transfer and low interference across multiple tasks.
Researchers introduce SIGMAS, a self-supervised AI framework for identifying group structures in multi-agent swarms like drone fleets without ground-truth supervision. The system uses second-order interactions to infer latent group memberships from agent trajectories, demonstrating robust performance across diverse synthetic swarm scenarios.
Researchers introduce FM-RME, a foundation model for radio map estimation that combines geometry-aware feature extraction with attention-based neural networks. The model uses self-supervised pre-training to enable zero-shot generalization across spatial, temporal, and spectral domains without scenario-specific retraining.
Researchers introduce DyGnROLE, a new AI architecture that better models directed dynamic graphs by treating source and destination nodes differently. The system uses role-specific embeddings and a self-supervised learning approach called Temporal Contrastive Link Prediction to achieve superior performance on future edge classification tasks.
Researchers developed a semi-supervised machine learning pipeline using vision transformers and k-Nearest Neighbor classifiers to automatically detect poor-quality exposures in astronomical imaging surveys. The method was successfully applied to the DECam Legacy Survey, identifying 780 problematic exposures that were verified through visual inspection.
Researchers developed TokEye, a self-supervised AI framework that can extract coherent signals from noisy time-series data in 0.5 seconds, initially designed for fusion reactor diagnostics. The system demonstrates applications beyond fusion research, including bioacoustics, suggesting broader potential for real-time signal processing across industries.
