TuneJury: a model trained on human judgments predicts music preferences
mittu1204 · x · 2026-11-03
Researcher yonghyunkim introduces TuneJury, a model that learns from human judgments to predict music preferences. Its scores can be used to compare tracks, filter music datasets, and more. chrisdonahuey endorses it as "incredibly useful," already applied to data filtering and follow-up model improvement work.
More from Multimodal
- Testing HeyGen Video 1's creative limits with two distinct prompt styles — toolstelegraph · 2026-11-03
- HeyGen CEO: open models will win video and voice just like they did LLMs — toolstelegraph · 2026-11-03
- Cosmos 3 world model follows camera controls from a single image, recipe released — NVIDIAAI · 2026-11-03
- NVIDIA Cosmos Simulation Recipes Turn Daytime Drives Into Rainy Nights With Trajectories Intact — NVIDIAAI · 2026-11-03
- Suno user begs for a button that writes prompts so they never have to — gleech · 2026-11-03
- Seedance 2.5 demo: a 30-second swamp creature short film made in Dreamina — LudovicCreator · 2026-11-03