arXiv Machine Learning July 24, 2026 By Joseph An, Phillip Keung, Jiaqi Wang, Orevaoghene Ahia, Noah A. Smith

Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization

Read the original on arXiv Machine Learning →

arXiv:2602. 10230v2 Announce Type: replace Abstract: Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding.

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

llms

arXiv AI

Jul 7

Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding

arXiv:2607. 04383v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set.

By Zihan Zhang, Xize Cheng, Wenhao Yan, Tong Zhang, Dongjie Fu, Boyun Zhang, Yongbo He, Tao Jin

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 29

Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding

arXiv:2606. 27320v1 Announce Type: cross Abstract: Neural audio autoencoders have become a core component of compression, feature extraction, and generation.

By Dimitrios Bralios, Paris Smaragdis, Minje Kim

arXiv AI

Aug 11

VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference

arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.

By Wenxu Jia, Dongjie Fu, Xize Cheng, Fangming Feng, Linjun Li, Wenshi Chen, Yingming Li, Zhou Zhao, Tao Jin

llms efficiency multimodal benchmarks safety

arXiv AI

Jul 7

StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

arXiv:2604. 19635v2 Announce Type: replace-cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications.

By Shuhai Peng, Hui Lu, Jinjiang Liu, Liyang Chen, Guiping Zhong, Jiakui Li, Huimeng Wang, Haiyun Li, Liang Cao, Shiyin Kang, Zhiyong Wu

llms benchmarks

arXiv AI

Jun 2

MOSS-Audio Technical Report

arXiv:2606. 01802v1 Announce Type: cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning.

By Chen Yang, Chufan Yu, Hanfu Chen, Jie Zhu, Jingqi Chen, Ke Chen, Wenxuan Wang, Yang Wang, Yaozhou Jiang, Yi Jiang, Zhengyuan Lin, Ziqi Chen, Zhaoye Fei, Chenghao Liu, Jun Zhan, Kang Yu, Kexin Huang, Mingshu Chen, Qinyuan Cheng, Ruixiao Li, Shimin Li, Songlin Wang, Yang Gao, Yiyang Zhang, Xipeng Qiu

llms agents nlp fine-tuning multimodal

arXiv AI

Jun 2

FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation

arXiv:2601. 06199v3 Announce Type: replace-cross Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form speech is bottlenecked by the explosive growth of input tokens.

By Junseok Lee, Sangyong Lee, Chang-Jae Chun

llms multimodal benchmarks

Related stories

Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding

Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding

VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference

StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

MOSS-Audio Technical Report

FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation