arXiv AI August 5, 2026 By Guanrou Yang, Tian Tan, Qian Chen, Ziyang Ma, Yakun Song, Zhikang Niu, Qi Chen, Wenming Tu, Haitao Li, Shan Yang, Xie Chen

GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model

Read the original on arXiv AI →

arXiv:2608. 03215v1 Announce Type: cross Abstract: Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 9

End-to-End Training for Discrete Token LLM based TTS System

arXiv:2606. 09234v1 Announce Type: cross Abstract: Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently.

By Changfeng Gao, Yong Ren, Jun Yuan, Ye Bai, Zhao You, ShiDong Shang

llms diffusion nlp reinforcement-learning multimodal benchmarks

arXiv AI

Jun 8

dots.tts Technical Report

arXiv:2606. 07080v1 Announce Type: cross Abstract: We present dots.

By Shi Lian, Changtao Li, Bohan Li, Hankun Wang, Da Zheng, Junfeng Tian, Yufeng Ma, Colin Zhang, Kai Yu

diffusion efficiency multimodal benchmarks

arXiv AI

Aug 10

Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents

arXiv:2608. 06861v1 Announce Type: new Abstract: Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions.

By Hongxi Yan, Ziyue Huang, Shichao Fan, Qingjie Liu

llms agents multimodal

arXiv AI

Jun 2

ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate

arXiv:2606. 00257v1 Announce Type: cross Abstract: Token-level credit assignment for language-model reinforcement learning is usually formulated as if the policy were fully trainable, while practical LLM-RL pipelines often rely on parameter-efficient fine-tuning, especially LoRA.

By Rodney Lafuente-Mercado

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 25

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

arXiv:2505. 12843v2 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback (RLHF) relies on reward models to align large language models with human preferences.

By Kangwen Zhao, Jianfeng Cai, Jinhua Zhu, Ruopei Sun, Dongyun Xue, Wengang Zhou, Li Li, Houqiang Li

llms reinforcement-learning safety

arXiv Machine Learning

Aug 5

Latent Reward Registers for Diffusion Preference Alignment

arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.

By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun

llms diffusion reinforcement-learning efficiency benchmarks safety

Related stories

End-to-End Training for Discrete Token LLM based TTS System

dots.tts Technical Report

Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents

ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

Latent Reward Registers for Diffusion Preference Alignment