Tag
The paper establishes a theoretical framework showing that data and memory resources in autoregressive prediction are governed by a single predictive-energy spectrum, providing a joint scaling law.
NAPE is a self-supervised audio learning framework that uses causal Transformers to predict next spectrogram patch embeddings, achieving state-of-the-art performance on multiple audio and speech benchmarks with a minimalist design.
ABot-M0.5 is a new World Action Model for mobile manipulation that improves performance through temporal granularity alignment, action space disentanglement, and train-test consistency, achieving state-of-the-art results on long-horizon and fine-grained manipulation benchmarks.