Event Schedule

GenAI4SM 2026 @ WSDM


Opening

Time Event
08:55 - 09:00 Opening Remarks: Organizers

Session 1: 09:00 - 10:30

Time Talk
09:00 - 09:45 Keynote. Shivam Verma / Spotify
From Multi-Task Recommender Systems to Catalog-Grounded Personalization at Scale
09:45 - 10:00 Paper. Mahesh Jindal, Giuseppe Di Benedetto and Yannik Stein
Why One Size Doesn't Fit All: Improving Music Discovery and Familiar Listening with Specialized Models (Amazon Music, Audible)
10:00 - 10:15 Paper. Kirandeep Kaur and Amit Goyal
Cold-Start Audiobook Recommendation via Cross-Domain Sub-Tower Fusion (Amazon Music)
10:15 - 10:30 Paper. Sudheer Tubati and Amit Goyal
SAGE: Scalable Automatic Gating Ensemble for Confident Negative Harvesting in Fraud Detection (Amazon Music)

☕ Coffee Break: 10:30 - 11:00


Session 2: 11:00 - 12:45

Time Talk
11:00 - 11:45 Keynote. Thorsten Joachims / Cornell University
Towards Steerable GenAI for Recommendation
11:45 - 12:00 Paper. Abhishek Dharmaratnakar, Srivaths Ranganathan, Debanshu Das and Anushree Sinha
Generative AI for Video Trailer Synthesis: From Extractive Heuristics to Autoregressive Creativity (Google)
12:00 - 12:45 Keynote. Harald Steck / Netflix
On Collaborative Filtering for Conversational Recommender Systems

🍽️ Lunch: 12:45 - 13:45


Session 3: 13:45 - 15:30

Time Talk
13:45 - 14:30 Keynote. 'YZ' Yezhou Yang / Arizona State University
Towards Controllable and Explainable Visual GenAI for Creativity
14:30 - 14:45 Paper. Liping Zhang and Tracy King
VTCR: Multimodal Visual–Text Cross-Attention Reranking for Streaming Media and Creative Content Discovery (Adobe)
14:45 - 15:30 Keynote. Qilin Qi / Prime Video
Building Large-Scale Stream Prediction Models at Prime Video: Lessons from a Complex, High-Throughput Recommender System

☕ Coffee Break: 15:30 - 16:00


Session 4: 16:00 - 17:30

Time Talk
16:00 - 16:45 Keynote. Amanpreet Kaur and Ajay Yadav / Google
Quality at Scale: Engineering Evaluation Frameworks for Multi-Agent Systems
16:45 - 17:00 Paper. Ravi Gupta, Shiksha Patel, Nishant Singh and Ramya Kakarlapudi
DiTRoute: Diffusion-Guided Adaptive Token Routing for Distributed Video-LLM Inference on Heterogeneous Streaming Edges (AMD, Micron)
17:00 - 17:05 Closing Remarks: Organizers