IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu
cs.IR, cs.LG
Submitted: 2026-03-02
Updated: 2026-09-21
Comments: 20th ACM Conference on Recommender Systems (RecSys 2026) - Industry Track Paper, Oral Presentation
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning
- Test Time Embedding Normalization for Popularity Bias Mitigation
- Linguistic Knowledge and Transferability of Contextual Representations
- A Survey on Large Language Models in Multimodal Recommender Systems
- Decoupled Weight Decay Regularization
- Opening the Black Box of Deep Neural Networks via Information
- Does Representation Matter? Exploring Intermediate Layers in Large Language Models
- Layer by Layer: Uncovering Hidden Representations in Language Models
- MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding
- Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap
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
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG