Search-Aware On-Policy Self-Distillation with Sibling Alignment for Generative Recommendation
cs.LG, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- MLPs are Efficient Distilled Generative Recommenders
- Session-based Recommendations with Recurrent Neural Networks
- Distilling the Knowledge in a Neural Network
- MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation
- Gryphon-v2: One Model in Place of a Cascade - Generate-and-Rank Recommender with Rollout Distillation
- SCOReD: Student-Aware CoT Optimization for Recommendation Distillation
- UniSGR: Unified Framework for Semantic ID Generation and Ranking
- Learning from the Future: Privileged Self-Distillation for Sequential Recommendation
- TIP: Token Importance in On-Policy Distillation
- SmartGR: Hierarchy and Beam-Aware Knowledge Distillation for Generative Recommendation
- TopoGR: Revealing and Preserving Latent Structure of Semantic ID in Generative Recommendation
- EvoReason: Self-Evolving Reasoning Primitive-Guided On-Policy Distillation for Latent Reasoning in Generative Recommendation
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis