arXiv AI July 24, 2026 By Pengfei Zhang, Tianxin Xie, Minghao Yang, Li Liu

AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching

arXiv:2603. 01006v3 Announce Type: replace-cross Abstract: REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher features, but its effectiveness in token-conditioned audio Flow Matching critically depends on the choice of supervised layers, which is typically made heuristically based on the depth.

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

arXiv AI

Jun 9

BareWave: Waveform-Native Flow-Matching Text-to-Speech

arXiv:2606. 09048v1 Announce Type: cross Abstract: Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling.

By Wei Fan, Chao-Hong Tan, Qian Chen, Wen Wang, Xiangang Li, Kejiang Chen, Weiming Zhang, Nenghai Yu

multimodal safety

arXiv AI

Jul 13

ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models

arXiv:2607. 09134v1 Announce Type: cross Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity.

By Sang-Hoon Lee, Ha-Yeong Choi

llms diffusion multimodal safety

arXiv AI

Jul 9

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs

arXiv:2607. 06831v1 Announce Type: cross Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio.

By Albert Zeyer, Ralf Schl\"uter, Hermann Ney

llms multimodal safety

arXiv AI

Jun 10

Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation

arXiv:2606. 10368v1 Announce Type: cross Abstract: Speech-to-text (S2T) systems for recognition (ASR) and translation (S2TT) typically generate discrete text tokens.

By Xuanchen Li, Tianrui Wang, Yuheng Lu, Zikang Huang, Yu Jiang, Chenghan Lin, Chenrui Cui, Ziyang Ma, Xingyu Ma, Chunyu Qiang, Guochen Yu, Xie Chen, Longbiao Wang, Jianwu Dang

diffusion multimodal

arXiv AI

1d ago

Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer

arXiv:2608. 15690v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output.

By Ivan Mikheev, Viacheslav Vasilev, Anna Dmitrienko, Alexey Letunovskiy, Ivan Kirillov, Kirill Chernyshev, Denis Dimitrov

rag diffusion fine-tuning 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

Related stories

BareWave: Waveform-Native Flow-Matching Text-to-Speech

ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs

Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation

Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer

dots.tts Technical Report