Similar Items: Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale
- Living Databases: A Unified Model for Continuous Schema Evolution, Versioning, and Transformations
- Health System Scale Semantic Search Across Unstructured Clinical Notes
- LUCAS-MEGA: A Large-Scale Multimodal Dataset for Representation Learning in Soil-Environment Systems
- QuIVer: Rethinking ANN Graph Topology via Training-Free Binary Quantization
- Write-Read Decoupling in Modern Large-Scale Search Engines: Architectures, Techniques, and Emerging Approaches
- Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies