Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Yanfeng, Cai, Pengfei, Liu, Jun, Gu, Qing, Jiang, Nan, Dai, Lirong, McLoughlin, Ian, Song, Yan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.13715
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915938581872640
author Shi, Yanfeng
Cai, Pengfei
Liu, Jun
Gu, Qing
Jiang, Nan
Dai, Lirong
McLoughlin, Ian
Song, Yan
author_facet Shi, Yanfeng
Cai, Pengfei
Liu, Jun
Gu, Qing
Jiang, Nan
Dai, Lirong
McLoughlin, Ian
Song, Yan
contents Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, these models still face challenges in temporal perception (e.g., inferring event onset and offset), leading to limited utility in fine-grained scenarios. To address this issue, we propose Audio-Side Time Prompt and leverage Reinforcement Learning (RL) to develop the TimePro-RL framework for fine-grained temporal perception. Specifically, we encode timestamps as embeddings and interleave them within the audio feature sequence as temporal coordinates to prompt the model. Furthermore, we introduce RL following Supervised Fine-Tuning (SFT) to directly optimize temporal alignment performance. Experiments demonstrate that TimePro-RL achieves significant performance gains across a range of audio temporal tasks, such as audio grounding, sound event detection, and dense audio captioning, validating its robust effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13715
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt
Shi, Yanfeng
Cai, Pengfei
Liu, Jun
Gu, Qing
Jiang, Nan
Dai, Lirong
McLoughlin, Ian
Song, Yan
Sound
Artificial Intelligence
Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, these models still face challenges in temporal perception (e.g., inferring event onset and offset), leading to limited utility in fine-grained scenarios. To address this issue, we propose Audio-Side Time Prompt and leverage Reinforcement Learning (RL) to develop the TimePro-RL framework for fine-grained temporal perception. Specifically, we encode timestamps as embeddings and interleave them within the audio feature sequence as temporal coordinates to prompt the model. Furthermore, we introduce RL following Supervised Fine-Tuning (SFT) to directly optimize temporal alignment performance. Experiments demonstrate that TimePro-RL achieves significant performance gains across a range of audio temporal tasks, such as audio grounding, sound event detection, and dense audio captioning, validating its robust effectiveness.
title Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2604.13715