Tag
GeoRVQ introduces a decoder-aware masked token model for physiological signals that improves accuracy and reduces decoded distortion by accounting for local response and residual dependencies in residual vector quantization.
This paper proposes masked depth modeling with sensor-validity masking, achieving best RMSE on 7 out of 8 masked/sparse depth benchmarks, with a controlled encoder-init study.
This paper introduces AnyMo, a unified multimodal framework for human motion generation that combines a Residual FSQ-based motion tokenizer with a scalable masked modeling transformer, along with the OmniHuMo dataset of over 5,000 hours of motion data to enable high-quality synthesis under arbitrary modality combinations.
AudioMosaic introduces a contrastive learning-based audio encoder that uses structured time-frequency masking on spectrogram patches for efficient large-batch training, achieving state-of-the-art performance on audio benchmarks and improving audio-language models.
CSI-JEPA is a self-supervised framework for learning reusable representations from unlabeled Wi-Fi channel state information, enabling label-efficient multi-task sensing. It achieves up to 98% label savings and outperforms supervised models.