Zeyi Wen

19 papers · 2018–2026 · 8 conferences · across top CS/AI conferences

Achievements

+8 more ↓

🧭 Keyword Pioneer 🐝 Cross-Pollinator (10) 🌍 Conference Polyglot (7) 🏃 Academic Marathon (7) 🌈 Renaissance Researcher (7)

🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (50) 🌍 Conference Polyglot (7) 🏆 Keyword Champion (4) 💎 Century Club (16) 🗃️ Keyword Collector (98) 📈 Trend Setter ⚡ Prolific Year (7)

Conferences

AAAI (6) EMNLP (4) ACL (2) IJCAI (2) JMLR (2) CVPR (1) ICLR (1) NAACL (1)

Top co-authors

Bingsheng He (6) Qinbin Li (5) Minping Chen (5) Zulong Chen (3) Hanfeng Liu (3) Ying Zhou (3) Jian Chen (3) Xinhao Huang (2) Bing Xu (2) Naveed Akhtar (2)

Research topics

Differential Privacy (1)

Keywords

large language model (5) gradient boosting decision tree (4) hyperparameter optimization (3) gpu computing (2) contrastive learning (2) reinforcement learning (2) multi-fidelity optimization (2) mixture of expert (2) privacy-preserving machine learning (2) ensemble learning (2) parallel computing (2) support vector machine (2) pre-trained language model (2) feature selection (1) natural language processing (1) sentiment analysis (1) convex optimization (1) federated learning (1) sentiment classification (1) feature learning (1)

Papers

Enhancing Online Recruitment with Category-Aware MoE and LLM-based Data Augmentation ACL 2026 Efficient Hyperparameter Optimization for LLM Reinforcement Learning ACL 2026 A Better Start: Sensitivity-Aware Warm-Up for Robust and Efficient Fine-Tuning AAAI 2026 Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions EMNLP 2025 SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression AAAI 2025 Towards Efficient Low-Order Hybrid Optimizer for Language Model Fine-Tuning AAAI 2025 EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference EMNLP 2025 SEAL: Structure and Element Aware Learning Improves Long Structured Document Retrieval EMNLP 2025 RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition IJCAI 2025 Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance NAACL 2025 Exploiting Careful Design of SVM Solution for Aspect-term Sentiment Analysis EMNLP 2024 Efficient Hyperparameter Optimization with Adaptive Fidelity Identification CVPR 2024 Local Path Integration for Attribution AAAI 2023 Re-calibrating Feature Attributions for Model Interpretation ICLR 2023 Challenges and Opportunities of Building Fast GBDT Systems IJCAI 2021 Privacy-Preserving Gradient Boosting Decision Trees AAAI 2020 ThunderGBM: Fast GBDTs and Random Forests on GPUs JMLR 2020 Practical Federated Gradient Boosting Decision Trees AAAI 2020 ThunderSVM: A Fast SVM Library on GPUs and CPUs JMLR 2018