MusicGen
PulseAugur coverage of MusicGen — every cluster mentioning MusicGen across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New 'Mental Damage' attack poisons AI music generation
Researchers have identified a new vulnerability in retrieval-augmented text-to-music generation systems, termed "Mental Damage." This attack involves poisoning the music caption database with crafted entries that subtly…
-
Persian MusicGen model fine-tuned with large dataset for cultural music generation
Researchers have developed a culturally-aware generative music model for Persian music, named Persian MusicGen. This model was fine-tuned using a newly curated dataset of over 900 hours of Persian audio samples, coverin…
-
Text-to-audio models show semantic fragility under prompt changes
A new research paper evaluates the semantic fragility of text-to-audio generation systems by testing how small changes in prompts affect audio output. The study used models like MusicGen and Stable Audio, introducing va…