The paper shows how to speed up reinforcement learning (RL) for large language models (LLMs) by making numbers smaller (FP8) without breaking training.

#FP8 quantization#LLM reinforcement learning#KV-cache

HeartMuLa: A Family of Open Sourced Music Foundation Models

Intermediate

Dongchao Yang, Yuxin Xie et al.Jan 15arXiv

HeartMuLa is a family of open-source music AI models that can understand and generate full songs with clear lyrics and strong musical structure.

#music generation#audio tokenizer#residual vector quantization

Prompt Repetition Improves Non-Reasoning LLMs

Beginner

Yaniv Leviathan, Matan Kalman et al.Dec 17arXiv

Repeating the entire prompt once (QUERY→QUERY+QUERY) helps many large language models answer better when you are not asking them to show their reasoning.

#prompt repetition#non-reasoning LLMs#causal attention