PPaperPicks

Yongqi Zhang

24 papers at tracked venues · 21 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. BubbleRAG: Interactive Cognitive Offloading with Thought Bubble in Retrieval-Augmented Generation
  2. Efficient Zero-Shot and Label-free Log Anomaly Detection for Resource-Constrained Systems
  3. EfficientTool: A Cost-Effective Aligning Framework for Tool-Conditioned Agents in SME Scenarios
  4. FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graph
  5. GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs
  6. HieraVisVR: Hierarchical Visual Analytics for Motion-Centric VR Playtesting
    CHI 2026 · Yongqi Zhang
  7. Probe-and-Fetch: Dynamic KV Cache Pruning for Accelerated Long-Context Inference in Web-Scale AI Search
  8. Retain to Refine: Adaptive Online Question Answering via Query Routing and Long-Short Memory
  9. Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA
  10. Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning
  11. An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework
  12. ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry
  13. Learning Crossmodal Interaction Patterns via Attributed Bipartite Graphs for Single-Cell Omics
  14. M2oERank: Multi-Objective Mixture-of-Experts Enhanced Ranking for Satisfaction-Oriented Web Search
  15. Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning
  16. OpenMEL: Unsupervised Multimodal Entity Linking Using Noise-Free Expanded Queries and Global Coherence
  17. Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research
  18. RankElectra: Semi-supervised Pre-training of Learning-to-Rank Electra for Web-scale Search
  19. RankExpert: A Mixture of Textual-and-Behavioral Experts for Multi-Objective Learning-to-Rank in Web Search
  20. Knowledge-Enhanced Recommendation with User-Centric Subgraph Network
  21. Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
  22. R²AG: Incorporating Retrieval Information into Retrieval Augmented Generation
  23. Triple-D: Denoising Distant Supervision for High-Quality Data Creation
  24. Understanding Expressivity of GNN in Rule Learning