Scholar
Yupeng Hou
Google Scholar ID: 447sLrkAAAAJ
University of California, San Diego
Citations & Impact
Citations
11,154
H-index
20
i10-index
25
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- ICML 2025 Spotlight: 'ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation' (first author)
- KDD 2025: 'Generating Long Semantic IDs in Parallel for Recommendation' (first author)
- ICDE 2024: 'Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation' (LC-Rec, co-author)
- KDD 2022: 'UniSRec'
- WWW 2023: 'VQ-Rec'
- ECIR 2024: 'LLMRank'
- Released Amazon Reviews 2023 dataset (570M reviews, 48M items, 60B tokens)
- Organized generative recommendation tutorials at WWW 2025 and CIKM 2025
Background
- PhD candidate at UC San Diego, advised by Prof. Julian McAuley
- Research interests: generative recommendation, action tokenization, and large language models (LLMs)
- Focuses on building AI systems that learn from human actions to better understand and interact with people
- Core research question: How should we represent human actions when building generative models?
- Recent work includes: Action tokenization, generative recommendation, and LLM-based recommendation
