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.

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 Machine Learning.

llms

arXiv AI

Sep 15

Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception

arXiv:2609.15215v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have substantially advanced general audio understanding, yet they remain limited in fine-grained temporal percept...

By Yanfeng Shi, Yan Song, Junhui Li, Tinggan Huang, Wu Guo, Haoyu Song, Ian McLoughlin

llms benchmarks

arXiv AI

Sep 1

TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models

TEMPO is a unified model that adds temporally‑grounded capabilities to large audio‑language models, enabling timestamping of events, speakers, and sounds in audio, speech, and music. It introduces a supervised fine‑tuning stage featuring atomic timestamp tokens, a time‑aware projector with sinusoidal encodings, and a distance‑aware Gaussian loss, trained via a synthetic‑to‑real curriculum. Additionally, TEMPO employs reinforcement learning (GRPO) as a refinement step, and achieves state‑of‑the‑art performance on a benchmark of 10K samples across five timestamping tasks, surpassing Audio Flamingo Next and Qwen3‑Omni.

By Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Utathya Aich, Ramani Duraiswami, Dinesh Manocha

llms rag reinforcement-learning fine-tuning multimodal benchmarks

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 AI

Aug 21

Towards Audio Token Compression in Large Audio Language Models

arXiv:2511. 20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.

By Saurabhchand Bhati, Samuel Thomas, Hilde Kuehne, Rogerio Feris, James Glass

llms computer-vision fine-tuning multimodal

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

Sep 15

LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation

arXiv:2605.27840v2 Announce Type: replace-cross Abstract: Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generatio...

By Zhisheng Zhang, Xiang Li, Yixuan Zhou, Jing Peng, Guoyang Zeng, Zhiyong Wu

llms diffusion nlp

One email a morning, machine-written

Related stories

Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception

TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models

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

Towards Audio Token Compression in Large Audio Language Models

Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding

LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation