Papers2

#temporal transformer

Next Embedding Prediction Makes World Models Stronger

George Bredis, Nikita Balagansky et al.Mar 3arXiv

NE-Dreamer is a model-based reinforcement learning agent that skips rebuilding pixels and instead learns by predicting the next step’s hidden features.

#model-based reinforcement learning#world models#next-embedding prediction

Not triaged yet

MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models

Intermediate

Yitian Gong, Kuangwei Chen et al.Feb 11arXiv

This paper builds a new audio tokenizer, called MOSS-Audio-Tokenizer, that turns sound into tiny tokens the way text tokenizers turn sentences into words.

#audio tokenizer#causal transformer#residual vector quantization

Not triaged yet