Steering Recommendations with Language: Rethinking Context at Spotify
Mounia Lalmas is Senior Director of Research and Head of Tech Research, Personalisation at Spotify, where she leads a team advancing the science and technology of personalization, spanning search, recommendation, user engagement, and evaluation. Her current focus is on how Generative AI transforms large-scale retrieval and recommendation, bridging foundational research and real-world impact. Before Spotify, she led research teams at Yahoo and held academic positions at the University of Glasgow and Queen Mary University of London. She has authored over 270 publications, served as Program Co-Chair for SIGIR, WWW, WSDM, and CIKM, and delivered keynotes at venues including RecSys and The Web Conference.

1. Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale
Ghazal Fazelnia, Paul Gigioli, Eliza Klyce, Sharon Zheng, Katie Zelvin, Ye Myat Thein, Anurag Deshpande, Seda Davtyan, Kate Remeika, Maya Hristakeva, Erik Franco, Karen Banzon, Peng Ge, Jacqueline Wood, Nandini Singh, David Murgatroyd, Mounia Lalmas, Yves Raimond and Andreas Damianou
2. Deciding When to Rely on Visual Information: Gated Multimodal Fusion in Sequential Recommendation
Natalija Glisovic, Danica Kragic and Martin Tegner
3. A Systematic Benchmark of Explainable Methods for Temporal Attribution in Sequential Recommendation Systems
Akash Pandey, Kanisha Shah, Addrish Roy, Hongyangyang Shi, Dwipam Katariya, Amanda Ding, Kalanand Mishra and Pranab Mohanty
4. Query- and Candidate-Aware Long User Sequence Modeling for Sponsored Product Ranking in Search
Dongyue Xie
5. SAGA: Structure-Attended Generative Action Foundation Model that encodes Multi-Surface User Action Sequences
Tsz Fung Pang, Po Jen Chen, Nimish Ronghe, Farhad Farahani and Bo Zhang
6. Seeing the Context: Enhancing Recommendations Systems with Image-Derived Contextual Signals
Tal Cordova, Moshe Unger and Tomer Geva