Tag
OmniSpectra 提出一种波长原生的光谱基础模型，采用连续坐标与物理约束解码器实现跨仪器表征学习，仅用 12.2M 参数即在八个巡天数据集上超越更大的基线模型，表明物理结构编码可以替代参数规模。
This paper studies self-supervised learning from continuous video streams using strict sliding-window batches, introduces the 95-hour WT++ urban walking-tour dataset, and proposes StreamMAE with stream-aware regularization and motion-biased crops to match i.i.d. MAE pretraining performance while scaling positively with stream size.
MANAS-2 introduces a new EEG foundation model using constrained reconstruction to enhance latent representations and improve performance on downstream tasks across multiple datasets.
This paper presents Tactus, an open-vocabulary tactile recognition model that maps low-cost pressure-array data to text embeddings, matching or exceeding a supervised closed-set CNN baseline on the STAG benchmark with only 187 training recordings and no classifier head.
This paper presents 3D masked autoencoders for volumetric microscopy data, demonstrating that 3D modeling outperforms 2D max-projection and slice-based variants on downstream single-cell tasks, with cross-modal alignment to a protein language model further improving performance.
Introduces BrainG3N, a dual-purpose tokenizer for 3D brain MRI latent diffusion using a frozen masked autoencoder encoder for clinically informative embeddings and a CNN decoder for reconstruction, achieving state-of-the-art performance on a 23-task benchmark and enabling controllable generation and longitudinal forecasting.
This paper proposes CoAD, a novel framework that unifies Outlier Exposure (classification) and Masked Autoencoder (reconstruction) paradigms for time series anomaly detection, addressing their respective limitations. Extensive experiments show that CoAD significantly outperforms state-of-the-art methods while being lightweight and fast.