arXiv AI August 11, 2026 By Yuanhe Zhang, Weiliu Wang, Jie Ren, Liang Lin, Zhenhong Zhou, Haoran Gao, Kun Wang, Chen Li, Li Sun, Sen Su

From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs

Read the original on arXiv AI →

arXiv:2608. 09158v1 Announce Type: cross Abstract: Large audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs.

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

arXiv Machine Learning

Jul 7

An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures

arXiv:2607. 03150v1 Announce Type: cross Abstract: While deepfake audio detection systems achieve high performance in controlled benchmarks, their reliability often diminishes in the wild.

By Santiago Rubio, Pilar Bello, Dayana Ribas, Antonio Miguel, Eduardo Lleida, Alfonso Ortega

benchmarks

arXiv Machine Learning

Jun 17

A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models

arXiv:2606. 17417v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) achieve strong performance on a variety of audio understanding tasks but continue to struggle with temporal reasoning, a fundamental capability central to human auditory perception.

By Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Sarah Wiegreffe, Dinesh Manocha, Ramani Duraiswami

llms fine-tuning benchmarks

arXiv AI

Jun 17

Membership Inference Attacks against Large Audio Language Models

arXiv:2603. 28378v2 Announce Type: replace-cross Abstract: We present the first systematic Membership Inference Attack (MIA) evaluation of LALMs.

By Jia-Kai Dong, Yu-Xiang Lin, Hung-Yi Lee

llms multimodal benchmarks

arXiv AI

Jun 8

SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models

arXiv:2606. 06907v1 Announce Type: cross Abstract: Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data.

By Seonuk Kim, Yonghyeon Jun, Ju Yeon Kang, Jimin Hong, Yoonhyeong Lee, Nam Soo Kim

llms fine-tuning benchmarks

arXiv AI

Jul 1

ASR-Agnostic Multimodal Spectrotemporal Modeling for Early Dementia Detection

arXiv:2606. 30646v1 Announce Type: cross Abstract: Speech recruits the same executive, attentional, and working memory processes underlying instrumental activities of daily living, or IADLs, providing a non-invasive proxy for cognitive assessment.

By Chukwuemeka Ugwu, Oluwafemi Richard Oyeleke

llms rag multimodal benchmarks

arXiv Machine Learning

Jun 4

FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors

arXiv:2606. 05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models.

By Sepehr Dehdashtian, Jacob H Seidman, Vishnu N Boddeti, Gaurav Bharaj

llms fine-tuning multimodal benchmarks safety

Related stories

An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures

A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models

Membership Inference Attacks against Large Audio Language Models

SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models

ASR-Agnostic Multimodal Spectrotemporal Modeling for Early Dementia Detection

FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors