PPaperPicks

Junwei Pan

18 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Cross-Scale Collaboration between LLMs and Lightweight Sequential Recommenders with Domain-Specific Latent Reasoning
  2. FEDIN: Frequency-Enhanced Deep Interest Network for Click-Through Rate Prediction
  3. Computational Advertising: Recent Advances
    WWW 2025 · Junwei Pan
  4. Crocodile: Cross Experts Covariance for Disentangled Learning in Multi-Domain Recommendation
  5. Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs
  6. From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
  7. Incremental Learning for LLM-based Tokenization and Recommendation
  8. Long-Sequence Recommendation Models Need Decoupled Embeddings
  9. Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models
  10. Towards Unifying Feature Interaction Models for Click-Through Rate Prediction
  11. Ads Recommendation in a Collapsed and Entangled World
    SIGKDD 2024 · Junwei Pan
  12. Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning
  13. Deep Pattern Network for Click-Through Rate Prediction
  14. Multi-Sequence Attentive User Representation Learning for Side-information Integrated Sequential Recommendation
  15. On the Embedding Collapse when Scaling up Recommendation Models
  16. STEM: Unleashing the Power of Embeddings for Multi-Task Recommendation
  17. Temporal Interest Network for User Response Prediction
  18. Understanding the Ranking Loss for Recommendation with Sparse User Feedback