FAVE replaces multi-step flow generation with a learned global average velocity from a semantic anchor prior, delivering SOTA accuracy and roughly 10x faster inference on recommendation benchmarks.
InProceedings of the 38th NeurIPS Conference on Neural Information Processing Systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation
FAVE replaces multi-step flow generation with a learned global average velocity from a semantic anchor prior, delivering SOTA accuracy and roughly 10x faster inference on recommendation benchmarks.