PulseAugur
EN
LIVE 15:16:11
ENTITY Mae

Mae

PulseAugur coverage of Mae — every cluster mentioning Mae across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
8
41 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
8
39 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
SENTIMENT · 30D

5 day(s) with sentiment data

RECENT · PAGE 1/3 · 60 TOTAL
  1. TOOL · CL_257188 ·

    MAETrack framework improves 3D object tracking by adapting pre-trained models

    Researchers have developed MAETrack, a new framework designed to improve the transferability of large-scale pre-trained models, specifically masked autoencoders (MAE), to the task of 3D single object tracking. The frame…

  2. RESEARCH · CL_257142 ·

    New framework optimizes 5G resource allocation using probabilistic forecasting

    Researchers have developed a new goal-oriented probabilistic forecasting framework to optimize resource allocation in 5G networks. This approach uses the Pinball Loss function with models like DeepAR and Temporal Fusion…

  3. RESEARCH · CL_256950 ·

    AI models for heart disease segmentation show poor out-of-distribution generalization

    A new research paper evaluates the out-of-distribution (OOD) generalization capabilities of deep learning models for segmenting congenital heart disease (CHD) anatomies. The study found that in-distribution performance …

  4. TOOL · CL_247746 ·

    Halo method improves forecast accuracy by estimating distribution scale

    Researchers have developed a method called Halo that enhances forecasting accuracy by estimating the scale parameter of a distribution alongside the location parameter. This approach, which reuses existing deep forecast…

  5. TOOL · CL_229623 ·

    New LUViT approach bridges LLM and Vision Transformer modality gap

    Researchers have developed Language-Unlocked Vision Transformers (LUViT), a novel approach to integrate Large Language Models (LLMs) with Vision Transformers (ViTs) for visual tasks. LUViT addresses the modality mismatc…

  6. TOOL · CL_229504 ·

    New framework adapts AI models for material recognition from sparse visual data

    A new framework called Sparse Surface Understanding Framework (SSUF) has been developed to improve material recognition from incomplete visual data. SSUF adapts four pre-trained architectures—ConvAE, ViT, Swin Transform…

  7. TOOL · CL_229418 ·

    New methods identify causal directionality in data with up to 84.3% accuracy

    Researchers have developed two new methods, Anticipated Asymmetric Geometries (AAG) and Monotonicity Index (MI), for identifying causal directionality in bivariate numerical data. The AAG method, which compares actual c…

  8. RESEARCH · CL_228917 ·

    New AI methods improve materials property prediction with scarce data · 4 sources tracked

    Researchers have developed new methods for predicting materials properties, particularly in scenarios with limited data. FrOGS, a discrete neural sampler, uses a hybrid approach combining autoregressive models with cont…

  9. TOOL · CL_218102 ·

    New AI model predicts train delays using Indian Railway Network data

    Researchers have developed RSTGCN, a novel Graph Convolutional Network designed to predict average train delays at stations. This model incorporates train frequency-aware spatial attention and has been tested on a newly…

  10. TOOL · CL_212141 ·

    New curriculum learning strategy boosts remote sensing AI efficiency

    Researchers have developed a new curriculum learning strategy for self-supervised learning in remote sensing. This method prioritizes samples based on their geographic isolation, a metric derived solely from geolocation…

  11. RESEARCH · CL_206016 ·

    New Framework FabriMAE Enhances VLA Model Self-Evaluation

    Researchers have developed FabriMAE, a novel self-evaluation framework for Vision-Language-Action (VLA) models. This framework, called Markov Attention Entropy (MAE), leverages internal visual modality entropy to assess…

  12. RESEARCH · CL_200197 ·

    AI accelerates Large Hadron Collider detector simulations with Normalizing Flows

    Researchers have developed a new method using fine-tuned Normalizing Flows (NFs) to speed up the simulation of particle detector responses at the Large Hadron Collider. This approach addresses the computational expense …

  13. TOOL · CL_198132 ·

    LSTM networks enhance electricity price prediction with adaptive learning

    Researchers have developed an adaptive online learning framework using Long Short-Term Memory (LSTM) networks to improve the accuracy of day-ahead electricity price predictions in the California energy market. The model…

  14. TOOL · CL_188741 ·

    Loss functions explained: MSE, MAE, Huber, and cross-entropy

    The article explains the dual role of loss functions in machine learning: quantifying errors and guiding model training through their derivatives. It details how Mean Squared Error (MSE) converges to the mean and Mean A…

  15. TOOL · CL_187485 ·

    New Curia-MAE method enhances 3D medical image segmentation

    Researchers have developed Curia-MAE, a new pre-training method for 3D medical image segmentation that aims to improve upon existing foundation models. This method incorporates a robust reconstruction objective, a featu…

  16. TOOL · CL_185199 ·

    MoCA framework enhances multi-modal wearable data analysis

    Researchers have introduced MoCA, a novel self-supervised learning framework designed for analyzing multi-modal data from wearable devices. This framework utilizes a transformer architecture combined with masked autoenc…

  17. TOOL · CL_181133 ·

    New SLiM framework unifies skeleton learning with compact tokens

    Researchers have developed SLiM, a novel framework for skeleton representation learning that unifies masked feature prediction and contrastive learning. This approach aims to overcome limitations in current methods by f…

  18. TOOL · CL_180936 ·

    Image generation difficulty depends on target representation, study finds

    A new research paper explores how different target representations impact image generation difficulty. The study compared raw pixels, SD-VAE latents, DINOv2, and MAE features within a unified masked autoregressive model…

  19. TOOL · CL_180934 ·

    Foundation model pretraining strategies impact retinal imaging transferability

    A new arXiv paper explores how different pretraining strategies for foundation models impact their effectiveness when transferred to ultra-widefield retinal imaging tasks. Researchers compared Vision Transformer encoder…

  20. TOOL · CL_180662 ·

    New framework audits volatility forecasts across market regimes

    This paper introduces a novel framework for auditing volatility forecasts, moving beyond aggregate accuracy metrics like RMSE and MAE. The proposed method identifies latent market regimes and evaluates forecast reliabil…