When Synthetic Speech Is All You Have: Better Call GRPO
arXiv:2607.08409v1 Announce Type: new Abstract: LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making…
Read the full articleYou might also wanna read
Study Finds Single Transformer Layer Can Match Full-Parameter RL Training in LLMs
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how
arxiv.org·7d agoStudy Finds Single Transformer Layer Can Match Full-Parameter RL Training in LLMs
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how
arxiv.org·7d ago
ConSPO: A Contrastive Approach to Improving Reinforcement Learning with Verifiable Rewards for LLMs
Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reaso
arxiv.org·1mo ago
Supervised Fine-Tuning as Reinforcement Learning: Introducing Importance-Weighted SFT
Behavior Cloning (BC) on curated (or filtered) data is the predominant paradigm for supervised fine-tuning (SFT) of large language models; a
arxiv.org·11mo ago
Hume AI Open-Sources TADA: Text-Acoustic Synchronization for Faster, More Reliable Speech Generation
TADA (Text-Acoustic Dual Alignment) is Hume AI's open-source speech-language model that synchronizes text and audio one-to-one.
hume.ai·4mo ago
LK Losses: A New Training Objective to Optimize Acceptance Rate in Speculative Decoding for LLMs
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate
arxiv.org·1mo agoImproving quality and robustness in LLM-based text-to-speech systems
Low-rank adaptation, data augmentation, and chain-of-thought reasoning are among the techniques enabling accent-free polyglot outputs, impro
Comments
Sign in to join the conversation.
No comments yet. Be the first.