HalluAudio is the first large-scale benchmark spanning speech, environmental sound, and music that uses human-verified QA pairs, adversarial prompts, and mixed-audio tests to measure hallucinations in large audio-language models.
Music Flamingo: Scaling music understanding in audio language models
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 12roles
background 1polarities
background 1representative citing papers
DialBGM is a new benchmark dataset revealing that existing AI models fall far short of human performance when recommending fitting background music for open-domain conversations.
Presents the ATTM grand challenge with efficiency and performance tracks for text-to-music generation using a public instrumental music dataset, evaluated via FAD, CLAP, a new CCS metric, and subjective tests.
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
Bagpiper-Edit performs zero-shot open-ended audio editing by translating natural-language instructions into edited rich captions that guide generation anchored to the original audio.
Acquisition route affects forgetting rates in multimodal models, with text-pathway knowledge forgetting faster than audio-pathway knowledge in music understanding tasks.
Black-box membership inference on text-to-music models reaches up to 98.6% accuracy by training an auditor on semantic alignment patterns extracted from shadow-model generations.
VocalParse applies interleaved and Chain-of-Thought prompting to a Large Audio Language Model to jointly transcribe lyrics, melody and word-note alignments, achieving state-of-the-art results on multiple singing datasets.
VTMR is a two-stage video-to-music recommender: joint audio-visual-text retrieval of candidates, then temporal-sequence reranking, lifting R@10 to 18.3 and matching commercial preference.
Introduces an OpenMIC-derived multi-axis benchmark sequence showing that high binary instrument QA accuracy fails to predict robust grounding, with models showing position bias, confusable errors, and temporal bias.
Score-aware training uses alignment scores to route low-quality segments into high-noise regimes as implicit regularizers, enabling a 450M model to rank competitively in a text-to-music challenge with limited data.
MOSS-Audio is an audio-language model using a 12.5 Hz encoder, DeepStack cross-layer injection, time markers, and an event-preserving annotation pipeline for unified audio understanding.
citing papers explorer
-
HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models
HalluAudio is the first large-scale benchmark spanning speech, environmental sound, and music that uses human-verified QA pairs, adversarial prompts, and mixed-audio tests to measure hallucinations in large audio-language models.
-
DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues
DialBGM is a new benchmark dataset revealing that existing AI models fall far short of human performance when recommending fitting background music for open-domain conversations.
-
Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods
Presents the ATTM grand challenge with efficiency and performance tracks for text-to-music generation using a public instrumental music dataset, evaluated via FAD, CLAP, a new CCS metric, and subjective tests.
-
Unified Audio Intelligence Without Regressing on Text Intelligence
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
-
Bagpiper-Edit: Zero-Shot Open-Ended Audio Editing via Rich-Caption
Bagpiper-Edit performs zero-shot open-ended audio editing by translating natural-language instructions into edited rich captions that guide generation anchored to the original audio.
-
When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting
Acquisition route affects forgetting rates in multimodal models, with text-pathway knowledge forgetting faster than audio-pathway knowledge in music understanding tasks.
-
Auditing Training Data in Generative Music Models via Black-Box Membership Inference
Black-box membership inference on text-to-music models reaches up to 98.6% accuracy by training an auditor on semantic alignment patterns extracted from shadow-model generations.
-
VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models
VocalParse applies interleaved and Chain-of-Thought prompting to a Large Audio Language Model to jointly transcribe lyrics, melody and word-note alignments, achieving state-of-the-art results on multiple singing datasets.
-
Multimodal Video-to-Music Recommendation via Semantic Retrieval and Temporal Reranking
VTMR is a two-stage video-to-music recommender: joint audio-visual-text retrieval of candidates, then temporal-sequence reranking, lifting R@10 to 18.3 and matching commercial preference.
-
Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models
Introduces an OpenMIC-derived multi-axis benchmark sequence showing that high binary instrument QA accuracy fails to predict robust grounding, with models showing position bias, confusable errors, and temporal bias.
-
Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation
Score-aware training uses alignment scores to route low-quality segments into high-noise regimes as implicit regularizers, enabling a 450M model to rank competitively in a text-to-music challenge with limited data.
-
MOSS-Audio Technical Report
MOSS-Audio is an audio-language model using a 12.5 Hz encoder, DeepStack cross-layer injection, time markers, and an event-preserving annotation pipeline for unified audio understanding.