Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
2 results for “semantic IDs”
SPIN Processed News Frame: The Hype
Off-Policy Evaluation for Semantic ID Recommenders: Does the Model's Own Code Hierarchy Help?
A new arXiv preprint proposes using the inherent hierarchical code structure (SID tree) of generative recommenders as a practical action abstraction for off-policy evaluation, enabling more reliable offline model selection when production A/B testing is scarce.
Spin 40% Claim Present in Source AI Risk Moderate
arXiv Machine Learning
Sep 1, 2026
SPIN Processed News Frame: The Hype
Presentation: From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash
DoorDash is replacing its legacy recommendation system with an agentic, context-aware AI architecture to improve relevance and conversion, using techniques like language-native consumer memory and RQ-VAE semantic IDs.
Spin 75% Needs Evidence AI Risk Moderate
InfoQ AI / ML / Data Engineering
Aug 15, 2026