SourceFlow: Collaborative Source Coupling for Flow-Based Recommendation
cs.IR
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Stochastic interpolants with data-dependent couplings
- Building Normalizing Flows with Stochastic Interpolants
- Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendation
- Designing a Conditional Prior Distribution for Flow-Based Generative Models
- Simple ReFlow: Improved Techniques for Fast Flow Models
- Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
- Flow Matching for Generative Modeling
- Flow Matching based Sequential Recommender Model
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Multisample Flow Matching: Straightening Flows with Minibatch Couplings
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation
- Improving and generalizing flow-based generative models with minibatch optimal transport
- Hierarchical Rectified Flow Matching with Mini-Batch Couplings
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA