EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment
cs.IR, cs.AI
Submitted: 2026-08-14
Updated: 2026-11-02
Comments: 10 pages, 10 figures, Under Review
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Differentiable Semantic ID for Generative Recommendation
- Multi-Token Prediction Needs Registers
- Better & Faster Large Language Models via Multi-token Prediction
- Reasoning over Semantic IDs Enhances Generative Recommendation
- Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation
- DeepSeek-V3 Technical Report
- DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation
- OneRec-Think: In-Text Reasoning for Generative Recommendation
- Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential
- Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning
- GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation
- EGA-V2: An End-to-end Generative Framework for Industrial Advertising
- Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction
- Pctx: Tokenizing Personalized Context for Generative Recommendation
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