Подборка статей 2025 (часть 3)

Attention-based ranking
- LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders
- TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation
- Twin-Flow Generative Ranking Network for Recommendation
- InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
- MARM: Unlocking the Recommendation Cache Scaling-Law through Memory Augmentation and Scalable Complexity
- GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction
- RankMixer: Scaling Up Ranking Models in Industrial Recommenders
- Climber: Toward Efficient Scaling Laws for Large Recommendation Models
- MTGR: Industrial-Scale Generative Recommendation Framework in Meituan
- Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation
- Make It Long, Keep It Fast: End-to-End 10k-Sequence Modeling at Billion Scale on Douyin
- OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommender
- Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders
- Practice on Long Behavior Sequence Modeling in Tencent Advertising
- Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation
- Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders
- From Features to Transformers: Redefining Ranking for Scalable Impact
- From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction
- Meta Lattice: Model Space Redesign for Cost-Effective Industry-Scale Ads Recommendations

Non-Two-Tower retrieval
- Autoregressive Generative Retrieval for Industrial-Scae Recommendations at Pinterest
- MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever
- MISS: Multi-Modal Tree Indexing and Searching with Lifelong Sequential Behavior for Retrieval Recommendation
- Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
- Bidding-Aware Retrieval for Multi-Stage Consistency in Online Advertising
- Equip Pre-ranking with Target Attention by Residual Quantization
- GRank: Towards Target-Aware and Streamlined Industrial Retrieval with a Generate-Rank Framework
- SilverTorch: A Unified Model-based System to Democratize Large-Scale Recommendation on GPUs
- DualGR: Generative Retrieval with Long and Short-Term Interests Modeling
- An Efficient Embedding Based Ad Retrieval with GPU-Powered Feature Interaction
- Hierarchical Structured Neural Network: Efficient Retrieval Scaling for Large Scale Recommendation