arXiv AI June 16, 2026 By Luca Della Libera, Cem Subakan, Mirco Ravanelli

WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation

arXiv:2603. 05299v2 Announce Type: replace-cross Abstract: Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information.

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 AI

Jul 3

An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation

arXiv:2607. 02119v1 Announce Type: cross Abstract: While Large Multimodal Models excel in comprehension, high-throughput inference engines lack native support for multimodal generation.

By Haoran Wang, Jinchuan Tian, Siddhant Arora, Shinji Watanabe

llms efficiency multimodal

arXiv Computation and Language

Sep 14

Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning

arXiv:2609.13045v1 Announce Type: new Abstract: Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-lingu...

By Hayato Futami, Hassan Shahmohammadi, Tushar Dhyani, Alkis Koudounas, Rapha\"el Lafargue, Yosuke Kashiwagi, Quentin Jodelet, Emiru Tsunoo

llms efficiency

Hugging Face Trending Papers

Jul 6

Unified Audio Intelligence Without Regressing on Text Intelligence

Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM.

llms rag agents reinforcement-learning efficiency multimodal benchmarks safety

arXiv AI

Jun 2

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

arXiv:2605. 29948v2 Announce Type: replace-cross Abstract: Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms.

By Bohan Li, Shi Lian, Hankun Wang, Yiwei Guo, Yu Xi, Zhihan Li, Da Zheng, Colin Zhang, Kai Yu

llms nlp

arXiv AI

Sep 10

HoliTok: A Continuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

arXiv:2605.29948v3 Announce Type: replace-cross Abstract: Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-qual...

By Bohan Li, Shi Lian, Hankun Wang, Yiwei Guo, Yu Xi, Zhihan Li, Da Zheng, Colin Zhang, Kai Yu

llms nlp

arXiv AI

Jul 7

Unified Audio Intelligence Without Regressing on Text Intelligence

arXiv:2607. 05196v1 Announce Type: cross Abstract: Audio intelligence involves understanding, reasoning about, and generating both audio and speech.

By Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim, Boxin Wang, Zihan Liu, Sungwon Kim, Yang Chen, Arushi Goel, Rajarshi Roy, Wenliang Dai, Zhuolin Yang, Yangyi Chen, Dongfu Jiang, Sreyan Ghosh, Tuomas Rintamaki, Andrew Tao, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping

llms rag agents reinforcement-learning efficiency multimodal benchmarks safety

One email a morning, machine-written

Related stories

An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation

Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning

Unified Audio Intelligence Without Regressing on Text Intelligence

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

HoliTok: A Continuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

Unified Audio Intelligence Without Regressing on Text Intelligence