PPaperPicks

Zeyi Wen

18 papers at tracked venues · 9 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. A Better Start: Sensitivity-Aware Warm-Up for Robust and Efficient Fine-Tuning
  2. Efficient Hyperparameter Optimization for LLM Reinforcement Learning
  3. Enhancing Online Recruitment with Category-Aware MoE and LLM-based Data Augmentation
  4. Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance
  5. EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference
  6. Efficient Mask Learning for Language Model Fine-Tuning
  7. Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions
  8. Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance
  9. KALE: Knowledge Aggregation for Label-free Model Enhancement
  10. RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition
  11. SEAL: Structure and Element Aware Learning Improves Long Structured Document Retrieval
  12. ScalaGBM: Memory Efficient GBDT Training for High-Dimensional Data on GPU
  13. SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression
  14. Tilia: Enhancing LIME with Decision Tree Surrogates
  15. Towards Efficient Low-Order Hybrid Optimizer for Language Model Fine-Tuning
  16. Efficient Hyperparameter Optimization with Adaptive Fidelity Identification
  17. Enhancing the Performance of Bandit-based Hyperparameter Optimization
  18. Exploiting Careful Design of SVM Solution for Aspect-term Sentiment Analysis