KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation
cs.IR
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/cxli2333/KuaiRecV2
Terminology
Sources
- OneRec Technical Report
- Towards Large-scale Generative Ranking
- From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- Fine-grained Semantics Integration for Large Language Model-based Recommendation
- Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks
- FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets
- Multi-Task Deep Recommender Systems: A Survey
- OneRec-Think: In-Text Reasoning for Generative Recommendation
- SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress
- Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation
- LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation
- MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation
- MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling
- Seq2Slate: Re-ranking and Slate Optimization with RNNs
- Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendation
- Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation
- Capturing User Interests from Data Streams for Continual Sequential Recommendation
- Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
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