473 citations
- Microsoft (United States)US3 papers
- National Institute of Standards and TechnologyUS3 papers
- University College LondonGB3 papers
- University of Maryland, College ParkUS3 papers
- Boise State UniversityUS2 papers
- Carnegie Mellon UniversityUS2 papers
- Center for Nanoscale Science and TechnologyUS2 papers
- Cornell UniversityUS2 papers
- Drexel UniversityUS2 papers
- Korea Institute of Science and TechnologyKR2 papers
- Massachusetts Institute of TechnologyUS2 papers
- Physical Measurement LaboratoryUS2 papers
30 papers
Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops
Enrico Palumbo, Alexandre Tamborrino, Victor Ode +15
Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g., "recommend Italian indie ar…
Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify
Shivam Verma, Hannes Karlbom, Yu Zhao +4
We present a unified multi-objective model for targeting both advertisements and promotions within the Spotify podcast ecosystem. Our approach addresses key challenges in personali…
Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge
Francesco Fabbri, Gustavo Penha, Edoardo D'Amico +7
Evaluating personalized recommendations remains a central challenge, especially in long-form audio domains like podcasts, where traditional offline metrics suffer from exposure bia…
Semantic IDs for Music Recommendation
M. Jeffrey Mei, Florian Henkel, Samuel E. Sandberg +2
Training recommender systems for next-item recommendation often requires unique embeddings to be learned for each item, which may take up most of the trainable parameters for a mod…
PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters
Azin Ghazimatin, Ekaterina Garmash, Gustavo Penha +14
Listeners of long-form talk-audio content, such as podcast episodes, often find it challenging to understand the overall structure and locate relevant sections. A practical solutio…
Prompt-to-Slate: Diffusion Models for Prompt-Conditioned Slate Generation
Federico Tomasi, Francesco Fabbri, Justin Carter +3
Slate generation is a common task in streaming and e-commerce platforms, where multiple items are presented together as a list or ``slate''. Traditional systems focus mostly on ite…