LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling

arXiv:2510.18239 · cs.IR, cs.LG · Submitted 2025-10-21 · Read on arXiv

cs.IR, cs.LG

Submitted: 2025-10-21

Updated: 2026-10-08

Terminology

• Transformer — 2× in this paper · explained in 2 episodes
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes

Sources

• Longformer: The Long-Document Transformer
• Efficient Long Sequential User Data Modeling for Click-Through Rate Prediction
• Rethinking Attention with Performers
• Flex Attention: A Programming Model for Generating Optimized Attention Kernels
• Key-Value Memory Networks for Directly Reading Documents
• FUM: Fine-grained and Fast User Modeling for News Recommendation
• Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
• Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS)
• Linformer: Self-Attention with Linear Complexity
• Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
• Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition