PPaperPicks

Yue Yu

National University of Defense Technology, National Laboratory for Parallel and Distributed Processing, China

36 papers at tracked venues · 28 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
  2. Dynamic Memory Forest: Constructing and Tracing Conversational Trajectories for Long-Term Conversation
  3. Fate: Fasss sEsdge Inference of Mixture-of-Experts Models via Cross-Layer Gate
  4. RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
  5. AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
  6. Are External Contributions Important to Project Productivity in Open Source Software? A Deep Insight based on Issue Entropy
  7. CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference
  8. COPR: Continual Human Preference Learning via Optimal Policy Regularization
  9. Causally Motivated Sycophancy Mitigation for Large Language Models
  10. Centrality-guided Pre-training for Graph
  11. Correcting Large Language Model Behavior via Influence Function
  12. Efficient Evolutionary Search Over Chemical Space with Large Language Models
  13. Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework
  14. OBDD-NET: End-to-End Learning of Ordered Binary Decision Diagrams
  15. Preference-Strength-Aware Self-Improving Alignment with Generative Preference Models
  16. RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization
  17. SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback
  18. Test-Time Adaptation of Medical Vision-Language Models with Mixture of Modality Experts
  19. VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting
  20. Whether LLMs Know If They Know: Identifying Knowledge Boundaries via Debiased Historical In-Context Learning
  21. At Which Training Stage Does Code Data Help LLMs Reasoning?
  22. BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers
  23. Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization
  24. EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records
  25. Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
  26. Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning
    ACL 2024 · Yue Yu
  27. GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning
  28. HYDRA: Model Factorization Framework for Black-Box LLM Personalization
  29. Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models
  30. MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning
  31. Multi-modal Stance Detection: New Datasets and Model
  32. Predicting Text Preference Via Structured Comparative Reasoning
  33. ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models
  34. RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records
  35. SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC
  36. SiFT: A Serial Framework with Textual Guidance for Federated Learning