Tootfinder

From Sound to Sight: Towards AI-authored Music Videos
Leo Vitasovic, Stella Gra{\ss}hof, Agnes Mercedes Kloft, Ville V. Lehtola, Martin Cunneen, Justyna Starostka, Glenn McGarry, Kun Li, Sami S. Brandt
https://arxiv.org/abs/2509.00029

From Sound to Sight: Towards AI-authored Music Videos
Conventional music visualisation systems rely on handcrafted ad hoc transformations of shapes and colours that offer only limited expressiveness. We propose two novel pipelines for automatically generating music videos from any user-specified, vocal or instrumental song using off-the-shelf deep learning models. Inspired by the manual workflows of music video producers, we experiment on how well latent feature-based techniques can analyse audio to detect musical qualities, such as emotional cues…

AI-Driven Generation of Data Contracts in Modern Data Engineering Systems
Harshraj Bhoite
https://arxiv.org/abs/2507.21056 https://arxiv.org/pdf/2507.21056…

AI-Driven Generation of Data Contracts in Modern Data Engineering Systems
Data contracts formalize agreements between data producers and consumers regarding schema, semantics, and quality expectations. As data pipelines grow in complexity, manual authoring and maintenance of contracts becomes error-prone and labor-intensive. We present an AI-driven framework for automatic data contract generation using large language models (LLMs). Our system leverages parameter-efficient fine-tuning methods, including LoRA and PEFT, to adapt LLMs to structured data domains. The mode…