arXiv AI June 10, 2026 By Nikita Koriagin, Georgii Aparin, Nikita Balagansky, Daniil Gavrilov

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

arXiv:2606. 10029v1 Announce Type: cross Abstract: Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

Sep 15

On the Interpretability of Whisper Encodings Using Sparse Autoencoders

arXiv:2605.12225v3 Announce Type: replace Abstract: While deep transformer-based models have advanced rapidly, their internal mechanisms remain largely a mystery. Recent work has prioritized understa...

By Dan Pluth, Zachary Nicholas Houghton, Yu Zhou, Vijay K. Gurbani

llms multimodal safety

arXiv Machine Learning

Sep 10

Interleaved Speech Language Models Latently Work In Text

arXiv:2606.22473v2 Announce Type: replace-cross Abstract: Speech language models (SLMs) increasingly combine speech and text, often by interleaving their tokens within a single sequence. Yet how thes...

By Talia Sternberg, Gallil Maimon, Yossi Adi

llms diffusion multimodal

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

Jun 9

GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model

arXiv:2512. 20978v2 Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech.

By Haoyang Li, Xuyi Zhuang, Azmat Adnan, Ye Ni, Wei Rao, Shreyas Gopal, Eng Siong Chng, Boon Siew Han, Yuanjin Zheng

llms rag reinforcement-learning safety

arXiv Computation and Language

Sep 16

SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages

arXiv:2601.09050v2 Announce Type: replace Abstract: Tonal low-resource languages are widely spoken but remain underserved by modern speech technologies. A central challenge is learning speech represe...

By Tianyi Xu, Xuan Ouyang, Binwei Yao, Shoua Xiong, Sara Misurelli, Maichou Lor, Junjie Hu

fine-tuning efficiency multimodal safety

arXiv Computation and Language

Sep 15

Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation

arXiv:2609.15313v1 Announce Type: cross Abstract: Autoregressive generation of interleaved text and acoustic tokens is a common approach to spoken-response generation in speech large language models....

By Daxin Tan, Dehua Tao, Chengxi Deng, Hanlin Zhang, Xiao Chen

llms fine-tuning efficiency multimodal

One email a morning, machine-written

Related stories

On the Interpretability of Whisper Encodings Using Sparse Autoencoders

Interleaved Speech Language Models Latently Work In Text

dots.tts Technical Report

GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model

SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages

Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation