We have 4 of 18 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Training data attribution for diffusion models aims to identify the training samples that influence a generated instance, but existing methods either require costly per-sample gradient computation or query-specific model optimization. Moreover, most methods attribute changes in a proxy loss rather than changes in the a...
MusTBench, a music-expert-validated benchmark designed to evaluate temporal grounding in LALMs through five temporally grounded question-answering tasks, is introduced, establishing temporal grounding as a key missing capability in current LALMs and position MusTBench as a challenging benchmark for future research in t...
This work designs a triplet-based forced-choice task comprising 300 cases, including plagiarism examples, cover songs, and AI-generated music, and introduces the MATCHA dataset, a collection of 1105 perceptual assessments of attribute-based music matches from 83 expert participants.
This framework produces both a transformation embedding and a processed-audio embedding, and it finds that the two play complementary roles: distance-based tasks favor the former, while probe-based tasks favor the latter.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
